WritersLogic agent-infra
com.writerslogic.agents/writerslogic-agent-infra
Micro agents for parsing, validation, encoding, scoring, and structured I/O pipelines.
Connect this server
One click to install, or copy the config below. Suits: Cursor · HTTP clients.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"writerslogic-agent-infra": {
"url": "https://agents.writerslogic.com/mcp/agent-infra"
}
}
}claude mcp add --transport http writerslogic-agent-infra https://agents.writerslogic.com/mcp/agent-infracode --add-mcp '{"name":"writerslogic-agent-infra","type":"http","url":"https://agents.writerslogic.com/mcp/agent-infra"}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Other
- Version
- 1.0.0
- Registry
- active
- Published
- 11/15/2026
Is it safe? Is it maintained?
Serverdex check: Nov 22, 2026Mostly fine: WritersLogic agent-infra is hosted endpoint answering without a key.
- Maintained
- No commit data
- The repository has not been read yet, so the last-commit date is unknown.
- Official registry
- Active
- Published as com.writerslogic.agents/writerslogic-agent-infra in the official MCP registry, version 1.0.0.
- Source
- No licence found
- Public repository, but GitHub reports no recognised licence. Check the README before shipping it in a product.
- Runs
- Hosted by the publisher
- Your client talks to agents.writerslogic.com: prompts and tool arguments leave your machine for that host.
- Credentials
- None needed to connect
- The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
- Owner
- Unclaimed
- Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.
Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.
Live check
checked Nov 22, 2026, 13:08 UTCStatus history & uptime →The endpoint answered the MCP handshake as "WritersLogic Verifiable AI Agent Hub-agent-infra" and listed 65 tools. Answering since Nov 18, 2026.
Context cost ≈ 27k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 65 tools.
Tools (65)
warm-memory11 paramsWARM verifiable agent memory — Persistent memory for AI agents as a pay-per-call API, no database to run. op=remember stores subject-predicate-object facts (or extracts them from free text; only facts whose subject and object appear verbatim are kept); a newer value for the same subject and predicate supersedes the old one, and the history stays queryable. op=recall searches by BM25 keyword ranking or exact triple pattern, now
Show parametersHide parameters
opstringrequiredtenantIdstringRequired for API-key callers (namespace as key:<tenantId>; keep it unguessable). Ignored when a wallet paid.factsarraytextstringremember: free text; facts are extracted by a fast model and kept only if subject and object occur verbatim.sourcestringremember: provenance label for facts extracted from text.querystringpatternobjectExact (case- and whitespace-insensitive) match on any of subject, predicate, object.saidstringasOfEpoch milliseconds or an ISO 8601 date/time (UTC when no offset).limitintegerhistorystringrecall: only facts current at asOf (default) or every status.
hash-receipt3 paramsSigned hash receipt (Merkle batch, RFC 9162) — Timestamped, signed receipt for up to 256 SHA-256 hashes in one call: an RFC 9162 Merkle root, a per-hash inclusion proof, and the hub's W3C VC + EIP-191 signatures over both. For agents that need third-party evidence of what they did and when (action logs, generated files, prompts, tool outputs) without sending the data itself. Pure code, no model; verify free at /api/v1/verify-provenance.
Show parametersHide parameters
hashesarrayrequiredSHA-256 digests, 64 hex characters each. Hash your data locally; only the digests are sent.proofsbooleanReturn an inclusion proof per hash. Default true.labelstringOptional caller label (run id, job id) included in the signed receipt.
unicode-check2 paramsUnicode smuggling check for strings (prompts, tool args, URLs) — Checks up to 100 strings in one call against the 19 deterministic rules of unicode-safety-check: bidi controls (Trojan Source), invisible and zero-width characters, tag-character and variation-selector payloads, homoglyph and mixed-script hosts or names. Built for an agent's hot path: run it on a prompt, a tool argument, a URL or a model output before acting on it. Returns BLOCK / REVIEW / NO_FIND
Show parametersHide parameters
stringsarrayrequiredUp to 200000 characters in total.kindstringtext (default): prose, only critical findings block. identifier or url: high findings such as mixed-script names also block.
mcp-tool-pin3 paramsMCP tool pin: detect changed tool definitions (rug pulls) and hidden Unicode — Send an MCP server's tools/list result (up to 200 tools) and, after the first call, the hashes you approved. Returns a reproducible manifest hash, a per-tool hash, which tools were added, removed or changed since approval (silent description and schema edits are how MCP rug pulls and tool poisoning land), and Unicode smuggling findings in every name, description and schema string. Call it at sessi
Show parametersHide parameters
toolsarrayrequiredThe tools array from an MCP tools/list response, as received.approvedManifestHashstringmanifestHash from the call you approved.approvedToolsobjectMap of tool name to the per-tool hash you approved; enables the added/removed/changed diff.
doi-check1 paramDOI check: exists, retracted, or fabricated (batch of 20) — Checks up to 20 DOIs in one call against Crossref (including its Retraction Watch notices), OpenAlex and the doi.org Handle registry. Per DOI: FOUND with title and year, RETRACTED, EXPRESSION_OF_CONCERN, CORRECTED, REGISTERED_NOT_INDEXED, NOT_REGISTERED (no such DOI anywhere: likely fabricated), INVALID_DOI or UNVERIFIED. For research agents and RAG pipelines that cite papers: run every DOI throug
Show parametersHide parameters
doisarrayrequiredBare DOIs, doi: prefixes or https://doi.org/ URLs.
patch-anchor3 paramsApply a unified-diff hunk or search/replace edit to a file by content, refusing ambiguity — Applies unified-diff hunks (wrong line numbers are fine) or search/replace blocks to a supplied file text and returns the patched text, for an agent whose edit tool failed or whose diff has drifted line numbers. Each hunk is located by its content against the original file, trying exact, trailing-whitespace, outer-whitespace then collapsed-whitespace matching; the rung used is reported per hunk. I
Show parametersHide parameters
filestringrequiredCurrent file text, at most 524288 UTF-8 bytes and 100000 lines. A leading BOM is preserved.diffstringSingle-file unified diff, at most 64 hunks and 400 anchor lines each. Header counts and line numbers are ignored except as a reported hint. Give either diff oreditsarraySearch/replace blocks, matched as whole lines against the original file; all are located before any is applied.
edit-anchor-check3 paramsCheck that an edit's old-string occurs exactly once in a file, with match contexts — Counts how many times an old-string occurs in a supplied file text (as a replace-in-file tool would see it) and returns each match's offset, line, column and surrounding lines, for an agent about to issue an edit. pass: exactly one literal match, even counting overlapping ones. unknown: several matches, or one match that overlaps another occurrence of the same text (ambiguous; contexts show how to
Show parametersHide parameters
filestringrequiredFile text, at most 524288 UTF-8 bytes and 100000 lines.oldStringstringrequiredcontextLinesintegerLines of context before and after each listed match. Default 2.
retry-admissibility12 paramsDecide whether a failed HTTP call may be retried, must be reconciled, or must not be repeated — Given a request's method, how it ended (response status, timeout, reset, refused), idempotency-key evidence and optional caller policy, returns retry / do-not-retry / reconcile / unknown for an agent deciding what to do after a failed tool or API call. Encodes RFC 9110 method idempotency, the proxy and retry-of-a-retry rules and Retry-After parsing; a timeout or reset is never read as success or a
Show parametersHide parameters
methodstringrequiredHTTP method, case-sensitive (GET, POST, ...).endedstringrequiredHow the attempt ended.statusintegerRequired when ended is 'response'.requestSentstringWhether request bytes reached the network. connection-refused and dns-failure imply not-sent.idempotencyKeyobjectCaller-asserted evidence: the engine knows no vendor's key semantics.retryAfterstringRetry-After header value.attemptinteger1-based number of the attempt that just ended. Default 1.automaticbooleanTrue when the retry would be issued automatically (library or proxy) rather than by a deliberate decision.previousAttemptWasAutomaticRetrybooleanactorstringasOfstringRFC 3339 instant; needed only to turn a Retry-After HTTP-date into seconds.policyobject
http-outcome7 paramsClassify an HTTP response as success, retry, reconcile or stop, with the wait it asks for — Classifies one HTTP response (method, status, headers) as success / retry / reconcile / stop for an agent that just called an API, and reads the wait from Retry-After (RFC 9110: delay-seconds or any of the three HTTP-date formats) or from a vendor delay header whose dialect the caller declares (seconds, milliseconds, epoch seconds, epoch milliseconds, HTTP-date). Caller-supplied vendor rules (stat
Show parametersHide parameters
methodstringrequiredstatusintegerrequiredheadersarrayResponse headers as name/value pairs (names compared case-insensitively).delayHeaderobjectWhich header carries the wait and in what dialect. Default is Retry-After under RFC 9110.vendorRulesarrayFirst matching rule wins.idempotencyKeyobjectasOfstringRFC 3339 instant; needed to turn an HTTP-date or epoch delay into seconds.
mutation-intent4 paramsDiff a before/after JSON write for deletes, null-vs-omit and emptied arrays against protected paths — Compares the JSON document an agent read (before) with the one it is about to write (after) and lists every change by JSON Pointer: removed members, null turned into omitted (and the reverse), arrays emptied or shrunk, objects emptied, type changes. Fails when a change touches a protected path or is destructive and not listed in allowDestructive; use it before a PUT, PATCH or bulk update. Arrays a
Show parametersHide parameters
beforerequiredJSON value as last read.afterrequiredJSON value about to be written.protectedPathsarrayJSON Pointers that must not change at all; a "*" token matches any one key or index.allowDestructivearrayJSON Pointers ("*" wildcard) under which deletes, emptied containers and type changes are intended.
idempotency-fingerprint4 paramsDerive a stable idempotency fingerprint from declared identity fields and flag volatile fields — Hashes the fields you declare as the identity of an operation (JSON Pointers into each request) with RFC 8785 canonical JSON and SHA-256, so retries of the same operation get the same fingerprint regardless of key order, and flags the ways that breaks: an identity field missing, an identity field also declared volatile, identity values that look like timestamps, epoch times or UUIDs (heuristic), a
Show parametersHide parameters
requestsarrayrequiredidentityarrayrequiredJSON Pointers whose values define the operation's identity.volatilearrayJSON Pointers declared to change per attempt (timestamps, nonces, request ids).scopestringMixed into the hash (for example operation name and tenant) so equal bodies in different scopes get different fingerprints.
update-dialect5 paramsWhat do omitted, null, [] and "" mean in this PATCH body under merge-patch, JSON Patch or a declared dialect? — For an agent about to send a PATCH or update body: states, per field, what omitted / null / [] / "" mean under the declared dialect (RFC 7396 merge patch, RFC 6902 JSON Patch, or caller-declared semantics) and checks the body against stated intents such as 'clear this field', 'leave this alone' or 'set to empty array'. With a target document it applies the patch and compares the result; without on
Show parametersHide parameters
dialectstringrequiredmerge-patch = RFC 7396, json-patch = RFC 6902 (payload is an array of operations), caller = semantics in callerSemantics.payloadrequiredThe PATCH body.targetCurrent document, if available. Enables applying the patch and exact checks.intentsarraycallerSemanticsobjectRequired when dialect is 'caller': what each payload form means in that API.
pagination-loop2 paramsDetect repeated cursors, duplicate-only pages and no progress in a pagination scan — Takes the pages an agent has fetched so far (cursor used, next cursor returned, item ids) and finds the failures that make a scan loop or lie: a next cursor already used, a page whose items were all seen before, a page that returned nothing new yet offers another cursor, a scan that has not ended. Optionally takes declared ordering and cursor assumptions and lists the omission risks they imply (of
Show parametersHide parameters
pagesarrayrequireddeclaredobject
compensation-coverage2 paramsCheck that every write step in a multi-step plan has an undo step, and give the rollback order — For an agent plan made of steps with declared effects (read or write), checks every write in the plan, run or not, has a compensation step that exists, is itself a write, is not its own compensation, and that the dependencies have no cycle; flags writes declared irreversible; and, given which steps have completed, returns the compensations to run in reverse completion order. Does not judge whether
Show parametersHide parameters
stepsarrayrequiredcompletedarrayStep ids completed so far, in completion order. Only used for rollbackOrder and to say an irreversible write has already run; coverage is always checked for the
workflow-transition5 paramsIs this state transition allowed by the caller's workflow definition, and what is allowed instead? — Given a caller-supplied state machine (transitions with optional event names and required facts), the current state and a requested event or target state, says whether the transition is allowed, which required facts are false or unknown, and which transitions are available from the current state. For an agent about to move an order, ticket, deployment or approval to its next state. Terminal states
Show parametersHide parameters
transitionsarrayrequiredterminalarrayStates with no outgoing transitions allowed even if listed.currentstringrequiredrequestobjectrequiredGive event, to, or both.factsarray
deadline-feasibility3 paramsCan this plan of steps finish inside the remaining time, in the expected case and the worst case? — Takes steps with expected and worst-case durations, dependencies (steps with no dependency between them run in parallel), retries with backoff, and the time remaining, and computes the critical path for both cases. Verdict guaranteed (worst case fits: pass), likely (only the expected case fits: unknown) or infeasible (even the expected case does not fit: fail), with the slack and the critical-path
Show parametersHide parameters
stepsarrayrequiredremainingMsintegerrequiredTime left to the hard deadline, measured by the caller.overheadMsintegerFixed time to reserve for settlement, serialization, etc.
approval-invalidation9 paramsDoes a change to the approved thing invalidate the approval under a materiality policy? — Compares what a human or system approved with what is about to be executed (a quote, order, plan, diff summary: any JSON) under a caller-supplied materiality policy: per-path rules exact / ignore / numeric tolerance (absolute or percent) / no-increase / no-decrease, with the longest matching path winning and a default for unlisted paths. Also covers quote revisions (approved revision number must e
Show parametersHide parameters
approvedrequiredThe approved snapshot (JSON).currentrequiredThe version about to be executed (JSON).policyobjectapprovedRevisionintegercurrentRevisionintegerrequireSameRevisionbooleanDefault true when either revision is given (a missing partner gives unknown): an approval for another revision does not cover this one. Send false to ignore theapprovedAtstringRFC 3339 instant.validForSecondsintegerasOfstringRFC 3339 instant for the expiry check; no clock is read.
quota-reservation-check6 paramsWould this request fit in the remaining quota, given a snapshot and pending reservations? (snapshot-bound) — Computes available quota from a caller-supplied snapshot (limit, used, reserved) minus the unexpired pending reservations and says whether a requested amount fits. This is a read of the numbers you supply as of snapshotAt: it reserves nothing, so concurrent consumers can still use the quota before you do, and every response says so. A stale snapshot gives unknown, not pass; a window that ended at
Show parametersHide parameters
quotaobjectrequiredpendingarrayrequestobjectrequiredsnapshotAtstringrequiredRFC 3339 instant the quota numbers were read.asOfstringrequiredRFC 3339 instant of the decision (no clock is read).maxSnapshotAgeSecondsinteger
dedup-window4 paramsGroup webhook deliveries by identity within a time window and decide: process, dedupe, retry, reconcile or abstain — Given previously seen deliveries (identity, receivedAt, payload or digest, handling outcome) and a new incoming one, finds earlier deliveries with the same identity inside the window and returns process (none), dedupe (same payload already processed), retry (earlier ones all failed), reconcile (an earlier one is in flight or unknown, or the same identity arrives with a different payload) or abstai
Show parametersHide parameters
historyarrayrequiredincomingobjectrequiredwindowSecondsintegerrequiredwindowModestringfrom-first (default): a group's window starts at its first delivery. sliding: each delivery extends the window.
transcript-validator3 paramsCheck tool-call / tool-result pairing and ordering in an LLM transcript (Anthropic, OpenAI Chat, OpenAI Responses) — Validates a message list before it is sent to Anthropic Messages, OpenAI Chat Completions or OpenAI Responses: every tool call paired with its result, results in the right place and role, ids present and unique. Built for an agent that edits, truncates or replays its own history and would otherwise get a 400. Only rules stated in the providers' documentation fail the check; anything else suspiciou
Show parametersHide parameters
providerstringrequiredmessagesarrayrequiredexpectCompletebooleanDefault true: a trailing tool call without a result is a defect. Set false when the transcript is mid-loop and results are still pending.
cache-key-check5 paramsCheck that a result-cache key contains every input that changes the result, and nothing volatile — Given the inputs of a cached computation (each declared as influencing the output or not, optionally volatile) and the list of inputs the cache key is built from, finds influential inputs missing from the key (stale or wrong hits), volatile inputs inside it (the cache never hits), unknown-influence inputs left out, and, for private results, a missing tenant dimension (cross-tenant leak). When valu
Show parametersHide parameters
inputsarrayrequiredkeyPartsarrayrequiredNames of the inputs the key is built from.scopestringNamespace mixed into the digest.privatebooleanThe result is per-tenant or per-user.tenantInputstringName of the input that identifies the tenant or user; required in the key when private.
delegation-contract-check7 paramsCheck that a sub-agent delegation states objective, acceptance criteria, budget, evidence and stop conditions — Checks the brief an agent is about to hand to another agent: the required parts are present and non-empty (objective, acceptance criteria, a budget with at least one positive numeric bound, required evidence, stop conditions; output format if required), nothing is duplicated, and acceptance criteria are not made only of vague wording (a small labelled word list: good, appropriate, if possible ...)
Show parametersHide parameters
objectivestringacceptanceCriteriaarraybudgetobjectevidenceRequiredarrayWhat the delegate must return as proof (links, test output, file paths).stopConditionsarrayWhen the delegate must stop and report (done, blocked, budget spent).outputFormatstringrequirearrayParts that must be present. Default: objective, acceptanceCriteria, budget, evidenceRequired, stopConditions.
permission-intersection5 paramsEffective permissions of a delegated agent: requested ∩ user ∩ parent, minus explicit denials — Computes what a sub-agent may actually do: the permissions it requested, intersected with what the end user holds and what its parent agent holds, minus any explicit deny list, and says for each denied permission which party lacks it. Permission names are compared exactly (no wildcards); caller-declared implications (for example 'admin' grants 'read') can be given and are expanded transitively wit
Show parametersHide parameters
requestedarrayrequiredPermissions the delegate asks for.userarrayrequiredPermissions held by the end user.parentarrayrequiredPermissions held by the delegating agent.deniedarrayExplicit denials; they win over any grant.impliesarray
artifact-invalidator2 paramsWhich derived artifacts must be rechecked after these inputs changed? (bounded dependency graph) — Given a dependency graph of artifacts (each lists the artifact ids it was derived from) and the ids that changed, returns every artifact that transitively depends on a change, in an order safe to recompute (inputs before dependents), and the artifacts that are unaffected. A cycle or an unknown input id is a defect in the graph and returns fail with the cycle path. Changed ids that are unknown fail
Show parametersHide parameters
artifactsarrayrequiredchangedarrayrequired
assumption-conflict3 paramsFind assumptions that disagree across agents (currency, timezone, version, customer id, ...) — Takes assumptions that several agents or steps hold about the same fact (key, value, who) and reports every key where the values differ, naming the conflicting pairs and whether they differ only by case or whitespace (a formatting difference) or in substance (USD vs EUR, a different id, a different version). Optionally requires each listed agent to state each required key; a missing statement is u
Show parametersHide parameters
assumptionsarrayrequiredrequiredKeysarrayKeys every listed agent must state.agentsarrayAgents expected to state the required keys.
test-exit-interpret9 paramsInterpret a test run: pass, no-tests, skipped, flaky, infra-failure from runner, exit code and counts — Reads a finished test run (runner, exit code, optional version, flags, caller-parsed counts, optional go test output, optional per-attempt exit codes) and says whether tests actually passed, ran nothing, were all skipped, passed only on retry, or never ran properly (timeout, signal, internal error). Encodes only exit-code semantics the runners document: pytest 0-5, node:test, mocha (failure count
Show parametersHide parameters
runnerstringrequiredexitCodeintegerProcess exit status. Omit when the process was killed by a signal or timed out.signalstringTerminating signal name, e.g. SIGKILL.timedOutbooleanTrue when the harness gave up waiting.versionstringRunner version, e.g. 10.4.0. Needed only for version-gated flags.flagsobjectcountsobjectCounts parsed by the caller from the runner's own report.outputstringgo test output (only ok, FAIL, --- FAIL and panic: lines are read).attemptExitCodesarrayExit codes of repeated runs of the same tests, to detect flakiness. Interpreted with the same runner rules.
context-pack4 paramsPick context blocks that fit a token budget, keeping mandatory blocks and their dependencies — Chooses which context items an agent should put into a prompt without exceeding a token budget: every mandatory item and everything it depends on is always included, then optional items by descending priority (each with the dependencies it pulls in) while they fit. Token counts come from the caller or from o200k_base / cl100k_base; any other tokenizer name returns unsupported (there is no Claude t
Show parametersHide parameters
itemsarrayrequiredUp to 500 items, 300000 characters of text in total.budgetintegerrequiredMaximum total tokens (including perItemOverhead per included item).tokenizerstringo200k_base or cl100k_base. Any other name (including Claude models) returns status unsupported for items that need counting; caller token counts are always acceperItemOverheadintegerTokens added per included item for separators or wrappers. Default 0.
citation-span6 paramsLocate quoted text in a source with exact offsets, or classify it as normalized, elided, paraphrased or absent — Finds each quote an agent attributes to a source text and returns where it sits: exact offsets in UTF-16, code points, UTF-8 bytes and graphemes, so the span slices back to the matched text. Tries an exact match, then a match tolerant of whitespace, curly vs straight quotes, dash types, ellipses, invisible characters and Unicode forms (NFC/NFD, ligatures), naming which normalizations were needed,
Show parametersHide parameters
sourcestringrequiredText the quotes are claimed to come from.quotesarrayrequiredUp to 50 quotes, 40000 characters in total.ignoreCasebooleanAlso tolerate case differences (reported as a normalization). Default false.toleratearrayNormalizations that still count as a match. Default: all six.exactOnlybooleanCount only byte-identical matches as pass; normalized matches become fail. Default false.minLengthintegerQuotes shorter than this many characters (after trimming quote marks) are too-short and give unknown. Default 8.
constraint-carryover2 paramsCheck that earlier constraints (numbers, dates, codes, quoted terms, negations) survive into a later plan or summary — Takes the constraints an agent was given (budget caps, deadlines, identifiers, prohibitions) and a later artifact (plan, summary, handoff, tool arguments) and reports for each constraint whether its concrete atoms still appear: numbers with their unit or currency, ISO dates, codes, quoted terms, or caller-listed anchor strings, with offsets. For a negated constraint it also reports whether the clo
Show parametersHide parameters
constraintsarrayrequiredUp to 50; 20000 characters of constraint text in total.targetstringrequiredThe later artifact that must still honor the constraints.
evidence-bundle-check5 paramsCheck that every claim in an evidence bundle has enough independent, fresh, quote-verified support — Checks a bundle an agent assembled before answering: each claim must be backed by at least N evidence items from distinct source groups, each item's quote must actually appear in the supplied text (with offsets), publication dates must be within the caller's maximum age relative to a caller-supplied asOf, and duplicates are collapsed. Does not fetch URLs or judge whether a source is reliable or wh
Show parametersHide parameters
claimsarrayrequiredClaims to support.evidencearrayrequiredUp to 300 items; 300000 characters of text in total.asOfstringReference instant (ISO 8601) for age checks; required with maxAgeDays. The check never reads the clock.maxAgeDaysintegerEvidence published longer ago than this (relative to asOf) is stale.requireQuotesbooleanEvidence without a verifiable quote does not count as support. Default true.
syndication-hint4 paramsDetect near-duplicate passages (syndicated or copied text) so repeated sources are not counted as independent — Compares up to 30 passages an agent collected and reports which pairs share word-shingle content (Jaccard and containment), grouping them into clusters of probable copies so the number of independent sources can be stated honestly. Does not establish who copied whom, does not detect paraphrase or translation, and does not fetch anything; a high similarity is a hint that sources are not independent
Show parametersHide parameters
passagesarrayrequiredUp to 30; 300000 characters in total.shingleWordsintegerWords per shingle. Default 5.jaccardThresholdnumberPairs at or above this Jaccard similarity are flagged. Default 0.5.containmentThresholdnumberPairs where this share of the smaller passage's shingles appear in the other are flagged (catches an excerpt of a longer copy). Default 0.8.
hedge-extract2 paramsExtract hedging and certainty cues (may, probably, clearly, approximately) from text with offsets — Finds hedge and booster cues in an agent's or source's text using a fixed English lexicon (modals, epistemic verbs, adverbs and adjectives, approximators, shield phrases, certainty boosters) plus caller-supplied phrases, and returns each cue with its category, the sentence it sits in, and offsets in UTF-16, code points, UTF-8 bytes and graphemes. Rule-based and English only: a cue is a word match,
Show parametersHide parameters
textstringrequiredText to scan.extraCuesarrayCaller cues added to the lexicon.
negation-scope3 paramsFind negation cues and the words they cover; report whether given terms fall inside a negation scope — Applies NegEx-style rules (the English termset of negspacy, MIT, derived from NegEx) to text: finds negation cues, pseudo-negations such as 'not only', and scope terminators such as 'but', and returns each cue's scope window with offsets in UTF-16, code points, UTF-8 bytes and graphemes. Given target terms, reports per occurrence whether it is negated, not negated by the rules, or unknown (near a
Show parametersHide parameters
textstringrequiredText to analyze.targetsarrayTerms to classify (literal, case-insensitive, whole words).windowintegerWords a cue covers (NegEx uses 5). Default 5.
deictic-check3 paramsFind unresolved references (that one, the former, tomorrow, next week) and return clarification questions — Scans a user or tool message for phrases that cannot be understood without context: demonstratives ('that one', 'the latter'), back-references ('as before', 'the usual'), and relative dates or times ('tomorrow', 'next Friday', 'end of month', 'soon'), each with offsets and a clarification question. Given a caller anchor (asOf instant plus IANA time zone) it resolves only unambiguous day offsets (t
Show parametersHide parameters
textstringrequiredMessage to check.anchorobjectReference time for resolving unambiguous relative dates.candidatesarrayItems recently in play; echoed on reference slots for the caller to ask with. Never chosen automatically.
log-collapse4 paramsCollapse a log into error signatures with counts and first/last occurrence — Groups the records of a log or CI output by signature: timestamps, UUIDs, IPs, hex ids, quoted values and numbers are replaced by placeholders, stack-trace continuation lines are attached to their record and contribute their first frames, and each signature reports its count, severity, first and last line, first and last timestamp (as written, when the line starts with an ISO 8601 timestamp) and a
Show parametersHide parameters
textstringrequiredLog text, at most 8000 lines.topNintegerSignatures returned, by count. Default 20.signatureFramesintegerContinuation lines (stack frames) that are part of the signature. Default 3.minSeveritystringIgnore records below this severity. Default: keep all.
conversation-prune6 paramsChoose which old messages to drop to hit a token target without touching the cached prompt prefix — Given a conversation, the index of the last message inside the provider's cached prefix, and a token target, returns which messages to drop: whole tool call plus tool result pairs (so no result is left without its call) and messages the caller marked droppable, oldest first or largest first, never inside the cached prefix, never the most recent keepRecent messages, never pinned ones. Everything up
Show parametersHide parameters
messagesarrayrequiredUp to 500; 400000 characters of content in total.cacheBreakpointintegerrequiredIndex of the last message inside the cached prefix; -1 when nothing is cached.targetTokensintegerrequiredTotal tokens to get at or under.keepRecentintegerMost recent messages that are never dropped. Default 4.strategystringOrder in which droppable units are removed. Default oldest-first.tokenizerstringo200k_base or cl100k_base. Any other name (including Claude models) returns status unsupported for items that need counting; caller token counts are always acce
chunk-boundaries4 paramsSplit text into chunks under a hard token cap without cutting a table, sentence or code fence — Plans chunk boundaries for text an agent must feed to a model in pieces: every chunk is at most maxTokens in the named tokenizer (o200k_base or cl100k_base, verified by counting each finished chunk), boundaries fall only between sentences, blocks, whole Markdown or HTML tables and whole code fences, headings stay with the text that follows, and the chunks tile the input exactly (concatenating the
Show parametersHide parameters
textstringrequiredText to chunk (Markdown, plain text or HTML tables).maxTokensintegerrequiredHard cap per chunk.tokenizerstringrequiredo200k_base or cl100k_base. Any other name (including Claude models) returns status unsupported for items that need counting; caller token counts are always acceincludeTextbooleanAlso return each chunk's text. Default false (slice by span).
instruction-data-split2 paramsLabel spans of a prompt as pasted data or instructions, and flag instruction-like text inside the data — Splits an agent's input into data regions (code fences, block quotes, XML-style wrappers such as <document>, BEGIN/END markers, triple quotes, email headers with body, JSON blocks) and the text around them, labels each sentence outside the data as instruction (leading imperative verb or polite request) or unknown, and lists injection-style phrases found anywhere in the text ('ignore previous instr
Show parametersHide parameters
textstringrequiredThe full prompt or tool result to split.dataTagsarrayExtra XML-style tag names (letters, digits, underscore) whose content is data.
dom-skeleton3 paramsList the interactive elements of an HTML page with stable CSS selectors — Reduces an HTML document to the elements an agent can act on: links with href, buttons, inputs (not type=hidden), selects, textareas, [role], [onclick], contenteditable, each with tag, type, role, best-effort accessible name (including label associations) and a CSS selector that matches exactly that element, preferring a stable id, then a data-testid-style attribute, name, aria-label, then a struc
Show parametersHide parameters
htmlstringrequiredHTML source.maxElementsintegerMaximum elements returned. Default 100.dedupebooleanCollapse elements with identical tag, type, role, name and href. Default true.
dom-recipe-match3 paramsCheck whether a saved interaction recipe still applies to the current version of a page — Compares a recipe (ordered steps naming selectors from an earlier dom-skeleton call), the saved skeleton elements those selectors came from, and the current page HTML. Per step it reports matched (same selector, same tag, type, role and name), changed (selector still exists but the element differs), moved (the same element now has a different selector, given as newSelector), ambiguous (several cur
Show parametersHide parameters
recipeobjectrequiredsavedarrayrequiredelements from an earlier dom-skeleton response.htmlstringrequiredCurrent page HTML.
confirmation-state4 paramsClassify a confirmation message as submitted, pending, reserved or completed from caller or default phrases — Reads a confirmation page, email or API message and decides which state it states: submitted, pending, reserved or completed, using phrase lists the caller supplies (preferred, because wording is provider-specific) plus an optional default English list. Matches are whole-word, case- and typography-insensitive, returned with offsets in UTF-16, code points, UTF-8 bytes and graphemes, and a match ins
Show parametersHide parameters
textstringrequiredConfirmation text.rulesarrayCaller phrase lists; with these present the defaults are off unless useDefaults is true.useDefaultsbooleanInclude the default English phrases. Default true only when rules is absent.precedencearrayWhen several states match, the first one listed wins. Without it a conflict is unknown.
text-offsets4 paramsConvert text offsets between UTF-16, code points, UTF-8 bytes and graphemes, and locate hidden Unicode — Reports the length of a string in UTF-16 code units, Unicode code points, UTF-8 bytes and extended grapheme clusters (Intl.Segmenter), converts up to 200 ranges given in any one of those units into all four, and flags ranges that fall inside a surrogate pair, a multi-byte UTF-8 character or a grapheme cluster. It also runs the unicode-check rules (bidi controls, zero-width and invisible characters
Show parametersHide parameters
textstringrequiredThe string.rangesarrayHalf-open ranges to convert; each is read in its own unit.kindstringHow the unicode rules treat the string. Default text.scanbooleanRun the hidden-Unicode rules. Default true.
translation-invariants4 paramsCheck that numbers, units, part numbers, tolerance signs, dates, placeholders and URLs survive translation — For aligned source and target segments, extracts the tokens a translation must not change (numbers with attached units or %, ISO dates, part numbers and versions, tolerance and comparison operators such as ± ≤ ≥, placeholders like {0} or %s, URLs and emails) and reports any that are missing, added or altered, with offsets in both texts in UTF-16, code points, UTF-8 bytes and graphemes. Numbers are
Show parametersHide parameters
segmentsarrayrequiredUp to 200; 100000 characters in total.sourceDecimalstringDecimal mark of the source locale. Default auto (both readings tried).targetDecimalstringDecimal mark of the target locale. Default auto.kindsarrayToken kinds to check. Default all.
cross-reference-check1 paramFind dangling and duplicated cross-references (Section 3.2, Table 4, Figure 2, [7]) in a document — Scans a document for the targets it defines (numbered headings, Table/Figure/Listing/Equation captions at line start, Appendix/Annex headings, [n] bibliography entries, [^id] footnote definitions) and the references it makes to them ('see Section 3.2', 'Tables 2 and 4', 'Figures 3 to 5', '[7]', '[^note]'), and reports references with no target, targets defined twice, and targets never referenced,
Show parametersHide parameters
textstringrequiredDocument text (plain text or Markdown).
attachment-references2 paramsCheck that what a message says is attached matches the attachments actually supplied — Compares a message's wording with its attachment list: 'see attached' with nothing attached, a named file (report.pdf) that is not in the list, a kind of file mentioned (the spreadsheet, a screenshot, the PDF) that no attachment matches by extension or MIME type, and a stated count ('two files') that differs from the list; attachments the text never mentions are listed. Mentions inside a negation
Show parametersHide parameters
textstringrequiredMessage body.attachmentsarrayrequiredThe attachments actually present; may be empty.
footnote-attach4 paramsAttach footnote texts to their in-text markers from page layout coordinates — Given footnote markers (label, page, x, y) and footnote texts (label, page, x, y) extracted from a laid-out document, pairs each marker with its note by label and page, pairing repeated labels on one page in reading order, optionally letting a note continue on the next page, and reports unattached markers, orphan notes, ambiguous groups (different counts for the same label) and notes placed above
Show parametersHide parameters
markersarrayrequirednotesarrayrequiredyAxisstringDirection of increasing y: down (PDF.js, screen) or up (PDF user space). Default down.allowNextPagebooleanA note may sit on the page after its marker. Default false.
evidence-scope-mismatch3 paramsCheck that evidence covers the scope of the claim it is used for (geography, population, period, version, basis, unit) — Compares the scope descriptors of a claim and of the evidence offered for it, per dimension: geography and population (every claimed item must be equal to, or contained in a broader evidence item according to the caller's taxonomy), period (the evidence period must contain the claimed period; partial or no overlap is a mismatch), and version, basis and unit (must be equal after normalization). Des
Show parametersHide parameters
claimobjectrequiredScope of the claim being made.evidenceobjectrequiredScope of the evidence offered.taxonomyarrayContainment facts for geography and population (40,000 characters in total), e.g. {broader:'United States', narrower:['California','Texas']}. Transitive.
llm-watermark-detector8 paramsDetect LLM text watermark evidence: green-list z-test for a key you hold, plus invisible-character markers — Tests whether text carries watermark evidence, for a pipeline that must decide whether to trust or label content. Two independent checks: (1) a green-list z-test (Kirchenbauer et al. 2023) over green flags you supply, or over token ids and a key using this endpoint's own HMAC-SHA256 scheme, returning the z-score and exact binomial p-value; (2) an invisible-character scan of the text for zero-width
Show parametersHide parameters
textstringText to scan for invisible markers.greenFlagsarrayOne 0/1 per scored token: 1 when your own detector's green list contains the token. Deduplicate repeated n-grams yourself if your scheme requires it.tokenIdsarrayToken ids in order (at most 5000). Green membership is computed from the key with the hmac-sha256-green-1 scheme; each distinct consecutive pair is scored once.keystringSecret key for tokenIds. Used for this call only and never stored or echoed.schemestringScheme for tokenIds; default and only value.gammanumberExpected green fraction under no watermark. Default 0.25.zThresholdnumberz at or above which the result is fail. Default 4 (Kirchenbauer et al.).minTokensintegerFewer scored tokens than this is unknown. Default 25.
pacing-intensity-evaluator7 paramsPlot a prose intensity curve per sentence and flag where a tense passage loses velocity — Scores each sentence of narrative prose for pace from sentence length, share of one-syllable words, exclamation and question marks and, if you supply a word list, action-word share; smooths the scores into an intensity curve; and reports stalls, the spans where intensity falls well below an earlier peak. For a writing tool or editor agent checking an action or tension scene. A fixed-weight heurist
Show parametersHide parameters
textstringrequiredProse to score.actionWordsarrayYour own action-word list. Without it the action component is left out and the other weights are renormalized.expectstringtense: fail if the curve never reaches peakThreshold. any (default): only stalls after a peak can fail.windowintegerSentences in the trailing moving average. Default 3.stallDropnumberFall below the running peak that counts as a stall. Default 0.25 on the 0-1 intensity scale.peakThresholdnumberSmoothed intensity a passage must reach before a later fall can be a stall. Default 0.55.minSentencesintegerFewer scored sentences is unknown. Default 8.
markdown-syntax-shaper8 paramsNormalize sloppy model-generated Markdown to one house style, leaving code untouched — Rewrites Markdown from a language model into a consistent style and reports each edit by line: restores the space in '##Title', converts '*', '+' and '•' bullets to your chosen marker, strips trailing whitespace (keeping two-space hard breaks), collapses runs of blank lines, puts blank lines around headings and fenced blocks, closes a fence left open at the end, and ends the file with one newline.
Show parametersHide parameters
markdownstringrequiredMarkdown to normalize.bulletstringMarker for unordered lists. Default '-'.fixHeadingSpacebooleanRestore the space in '##Title'. A lowercase '#tag' at level 1 is treated as a hashtag and left alone. Default true.stripTrailingWhitespacebooleanDefault true; a two-space hard break before more paragraph text is kept.collapseBlankLinesbooleanCollapse runs of blank lines and drop leading and trailing blanks. Default true.blankLinesAroundBlocksbooleanInsert a blank line around headings and top-level fenced blocks. Default true.closeUnclosedFencebooleanAppend the closing fence when the document ends inside one. Default true.finalNewlinebooleanEnd with exactly one newline. Default true.
idempotency-registry9 paramsIdempotency registry: has key K already been done? Claim it, complete it, read the stored result — Shared memory for side-effecting operations across agents and retries. begin(key) answers proceed (you hold a short claim), wait (another owner is mid-flight), already_completed (returns the stored result pointer), or fingerprint_mismatch (same key, different operation). complete(key) records the result pointer; abandon(key) lets someone retry. The claim expires, so a crashed worker does not block
Show parametersHide parameters
opstringrequiredkeystringrequiredIdempotency key, e.g. refund:ch_123:2026-11-04.ownerstringWorker id; required for begin, complete and abandon.fingerprintstringHash of the operation's identity fields; a later begin with a different fingerprint is refused.claimSecondsintegerHow long a begin claim lasts; default 300.retentionHoursintegerHow long a completed key is remembered; default 24.resultobjectcomplete: where the outcome lives (do not store payloads here).tenantIdstringRequired for API-key callers (namespaced as key:<tenantId>; keep it unguessable). Ignored when a wallet paid: the payer address is the tenant.requestIdstringCaller-chosen id for this mutation. A retry with the same id and same input returns the stored response (24 h) instead of applying twice; the same id with diffe
lease7 paramsShort lease with fencing tokens: claim a task for N seconds, renew, release — Lets many agents agree which one works on a task: acquire a named resource for 1-3600 s, renew it while working, release it when done. Every new acquisition returns a strictly larger fencing token; pass it to the downstream store and reject writes carrying a smaller one, so a paused holder whose lease expired cannot clobber its successor. Re-acquiring as the current holder extends the lease with t
Show parametersHide parameters
opstringrequiredresourcestringrequiredTask or resource name, e.g. invoice:INV-1009 or deploy:prod.holderstringYour worker id. Required for acquire, renew and release.ttlSecondsintegerLease length; default 30.tokenintegerFencing token from acquire; required for renew and release.tenantIdstringRequired for API-key callers (namespaced as key:<tenantId>; keep it unguessable). Ignored when a wallet paid: the payer address is the tenant.requestIdstringCaller-chosen id for this mutation. A retry with the same id and same input returns the stored response (24 h) instead of applying twice; the same id with diffe
token-bucket7 paramsShared token bucket: many agents, one upstream rate limit — One rate limiter shared by every agent in your fleet. take(cost) atomically spends tokens if available and returns allowed plus remaining, or refuses with retryAfterMs until enough tokens refill. capacity and refillPerSecond are fixed when the bucket is first used; a call with different settings is refused so two fleets cannot silently disagree. Use a requestId so a retried take is not charged twi
Show parametersHide parameters
opstringrequiredbucketstringrequiredBucket name, e.g. openai:org-123:rpm.capacitynumberrequiredBucket size in tokens. Required on every call, peek included, and must equal the value the bucket was created with.refillPerSecondnumberrequiredTokens added per second (0.5 = one every 2 s). Required on every call; must equal the value the bucket was created with.costnumberTokens to spend; default 1.tenantIdstringRequired for API-key callers (namespaced as key:<tenantId>; keep it unguessable). Ignored when a wallet paid: the payer address is the tenant.requestIdstringCaller-chosen id for this mutation. A retry with the same id and same input returns the stored response (24 h) instead of applying twice; the same id with diffe
id-block6 paramsMonotonic id blocks: the next invoice or ticket numbers for a fleet of agents — Hands out strictly increasing integer blocks from a named sequence (1-1000 ids per call) so parallel agents never issue the same invoice, ticket or order number. Numbers are never reused. Not gapless: a block an agent reserves and never uses stays a gap, and if your call's payment fails after the block is written the same requestId returns that same block on retry. Legally gapless series must be a
Show parametersHide parameters
opstringrequiredsequencestringrequiredSequence name, e.g. invoice:2026.countintegerIds to reserve; default 1.startintegerFirst id of a new sequence; ignored once it exists. Default 1.tenantIdstringRequired for API-key callers (namespaced as key:<tenantId>; keep it unguessable). Ignored when a wallet paid: the payer address is the tenant.requestIdstringCaller-chosen id for this mutation. A retry with the same id and same input returns the stored response (24 h) instead of applying twice; the same id with diffe
spend-ledger9 paramsSpend ledger with reservations: one budget for a tree of agents — A budget shared by a task tree, in integer minor units. Call open(currency, budgetMinor) once per ledger first; every other op answers unknown NO_LEDGER until then. reserve() atomically holds an amount if the remaining budget covers it (expired holds are freed automatically); commit() records what was actually spent, up to the hold; release() frees a hold. These are real reservations, not a snapsh
Show parametersHide parameters
opstringrequiredledgerstringrequiredLedger name, e.g. task:research-42.currencystringopen: currency or token code, e.g. USD or USDC.budgetMinorintegeropen: total budget in minor units.reservationIdstringamountMinorintegerreserve: amount to hold. commit: amount actually spent (at most the hold).ttlSecondsintegerreserve: hold lifetime; default 600.tenantIdstringRequired for API-key callers (namespaced as key:<tenantId>; keep it unguessable). Ignored when a wallet paid: the payer address is the tenant.requestIdstringCaller-chosen id for this mutation. A retry with the same id and same input returns the stored response (24 h) instead of applying twice; the same id with diffe
result-cache6 paramsContent-addressed result cache shared by your agents (short TTL) — Caches a result under the SHA-256 of the canonical (JCS) request, so every agent in your fleet that makes the same request reuses one answer for up to an hour. get returns hit with the value and age, or a miss (status unknown). Scoped to your wallet or tenantId, never shared across customers, so nobody else can poison your cache.
Show parametersHide parameters
opstringrequirednamespacestringDefault: default.requestrequiredAny JSON identifying the computation; it is canonicalized (RFC 8785) and hashed.valueput: the JSON result, at most 16384 bytes serialized.ttlSecondsintegerput: default 300.tenantIdstringRequired for API-key callers (namespaced as key:<tenantId>; keep it unguessable). Ignored when a wallet paid: the payer address is the tenant.
policy-gate3 paramsPolicy gate with a signed receipt: your JsonLogic rules vs a proposed tool call or payment — Evaluates your own policy (JsonLogic rules, each allow or deny, deny-overrides or first-match, default deny) against a proposed tool call, payment or action, and returns allow or deny, the rule id that decided, and a receipt signed by the hub over the hashes of the policy, the request and the decision. The receipt is the product: another agent or an auditor can verify offline which rule allowed th
Show parametersHide parameters
languagestringDefault jsonlogic. cedar and rego return unsupported.policyrequiredJsonLogic: { rules: [{ id, effect: allow|deny, when: <JsonLogic>, description? }] (at most 100), combining?: deny-overrides|first-match, defaultEffect?: deny|alrequestrequiredThe proposed action as JSON (at most 65536 bytes), e.g. { tool, args, amountUsd, payee }. Rules read it with { "var": "args.amountUsd" }.
acceptance-receipt3 paramsSigned acceptance receipt: which deterministic tests a delivered output passed — Runs your deterministic acceptance tests (equals, exists, absent, type, contains, length and number ranges, one-of, sha256, a JSON Schema subset) against a sub-agent's or vendor's JSON output at JSON Pointer paths, and returns per-test results plus a hub-signed receipt over the output hash, the tests hash and the results. Use it before paying for delegated work or releasing the next step. It certi
Show parametersHide parameters
outputrequiredThe delivered JSON (at most 262144 bytes as JCS).testsarrayrequiredlabelstringFree text bound into the receipt, e.g. the task id.
fleet-memory7 paramsFleet memory: your agents' shared observations of endpoints, rate limits, IVR paths and ambiguous submissions — Lets every agent in your fleet record what it observed and read what the others saw, with freshness: endpoint brownouts and latency, rate-limit behaviour, IVR menu paths that worked, whether an ambiguous submission was later accepted or rejected, fixes for an error signature, stale feeds, page recipes, merchant workflow failures, document reputation. record() appends timestamped observations for a
Show parametersHide parameters
opstringrequirednamespacestringrequiredsubjectstringrequiredWhat was observed, e.g. api.stripe.com:POST:/v1/refunds, +18005551234:billing, or an error fingerprint.observationsarraysinceHoursintegerquery window; default 168 (7 days).tenantIdstringRequired for API-key callers (namespaced as key:<tenantId>; keep it unguessable). Ignored when a wallet paid: the payer address is the tenant.requestIdstringCaller-chosen id for this mutation. A retry with the same id and same input returns the stored response (24 h) instead of applying twice; the same id with diffe
micro-batch1 paramRun up to 20 micro checks under one payment ($0.02) — Bundles up to 20 calls to any pure micro check (catalog entries that are neither stateful nor network-reading, e.g. checksum, patch-anchor, allocate, business-deadline) into one x402 settlement, so a full batch costs $0.001 per check. Every call is validated before payment; one invalid call rejects the batch with its index. The request is capped at 128kb and a CPU weight of 40 (an ordinary check w
Show parametersHide parameters
callsarrayrequired
chat-fast6 paramsChat completion, fast tier (8k in, 1k out) — OpenAI-style chat completion served by the hub's provider router (small, fast model, up to 8000 input tokens and 1024 output tokens per call), with a signed receipt that binds the provider, model, token usage and the hashes of your messages and the reply. Supports optional strict json_schema output returned both parsed and as a string. Does not stream, call tools or functions, accept images, or us
Show parametersHide parameters
messagesarrayrequiredConversation, oldest first; the last message must have role user. At most 200000 characters in total. System messages are joined into the instructions.max_tokensintegerUpper bound on the reply in tokens; defaults to 1024. A value above the tier cap is rejected with 400.response_formatobjectEither {"type":"text"} (default) or {"type":"json_schema","json_schema":{name,schema}}. The schema is always enforced strictly: root object, every property requmodelstringAccepted and ignored: the hub routes by tier (the resource you paid for). Echoed as requested_model.temperaturenumberAccepted and ignored.top_pnumberAccepted and ignored.
chat-standard6 paramsChat completion, standard tier (12k in, 2k out) — OpenAI-style chat completion served by the hub's provider router (mid-size general model, up to 12000 input tokens and 2048 output tokens per call), with a signed receipt that binds the provider, model, token usage and the hashes of your messages and the reply. Supports optional strict json_schema output returned both parsed and as a string. Does not stream, call tools or functions, accept images,
Show parametersHide parameters
messagesarrayrequiredConversation, oldest first; the last message must have role user. At most 200000 characters in total. System messages are joined into the instructions.max_tokensintegerUpper bound on the reply in tokens; defaults to 1024. A value above the tier cap is rejected with 400.response_formatobjectEither {"type":"text"} (default) or {"type":"json_schema","json_schema":{name,schema}}. The schema is always enforced strictly: root object, every property requmodelstringAccepted and ignored: the hub routes by tier (the resource you paid for). Echoed as requested_model.temperaturenumberAccepted and ignored.top_pnumberAccepted and ignored.
chat-deep6 paramsChat completion, deep tier (12k in, 2k out) — OpenAI-style chat completion served by the hub's provider router (strongest available model, up to 12000 input tokens and 2048 output tokens per call), with a signed receipt that binds the provider, model, token usage and the hashes of your messages and the reply. Supports optional strict json_schema output returned both parsed and as a string. Does not stream, call tools or functions, accept imag
Show parametersHide parameters
messagesarrayrequiredConversation, oldest first; the last message must have role user. At most 200000 characters in total. System messages are joined into the instructions.max_tokensintegerUpper bound on the reply in tokens; defaults to 1024. A value above the tier cap is rejected with 400.response_formatobjectEither {"type":"text"} (default) or {"type":"json_schema","json_schema":{name,schema}}. The schema is always enforced strictly: root object, every property requmodelstringAccepted and ignored: the hub routes by tier (the resource you paid for). Echoed as requested_model.temperaturenumberAccepted and ignored.top_pnumberAccepted and ignored.
inbox-create2 paramsReceive-only inbox for agents without a public endpoint — Creates a receive-only inbox for an AI agent that has no public endpoint: a webhook URL that accepts POST or PUT, and (when the operator has configured inbound email) a unique email address. Pair with inbox-poll to read what arrived. It never sends email or calls out, does not store attachments, does not verify senders (no SPF/DKIM), and message content is untrusted third-party data. Inboxes live
Show parametersHide parameters
labelstringOptional name for your own bookkeeping.tenantIdstringRequired for API-key callers (namespace as key:<tenantId>; keep it unguessable). Ignored when a wallet paid.
inbox-poll7 paramsRead messages from a receive-only agent inbox — Returns the emails and webhook deliveries that arrived in an inbox you created with inbox-create, oldest first, with sender, subject, selected headers, a plain-text body (up to 64 KB per message in the response) and a sha256 of the stored body. Filter by since (inclusive), kind, limit up to 100; mark_consumed hides the returned messages from later polls unless include_consumed is true. It does not
Show parametersHide parameters
inbox_idstringrequiredtenantIdstringRequired for API-key callers (namespace as key:<tenantId>; keep it unguessable). Ignored when a wallet paid.sinceOnly messages received at or after this time: epoch milliseconds or ISO 8601 (UTC when no offset). Inclusive, so dedupe by id or use mark_consumed.kindstringDefault all.limitintegerDefault 50.mark_consumedbooleanMark the returned messages consumed. Default false.include_consumedbooleanAlso return consumed messages. Default false.
Checked by Serverdex with a plain initialize + tools/list call to agents.writerslogic.com/mcp/agent-infra, no credentials, about once a day. A failed check is never a removal.
Remotes
- streamable-http
https://agents.writerslogic.com/mcp/agent-infra
Alternatives to WritersLogic agent-infra
All WritersLogic agent-infra alternatives →Best Other servers →The most-starred Other servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| Labelhead Artist Momentum | 114,594 | Nov 2026 | Working |
| World Monitor | 91,002 | Nov 2026 | Needs sign-in |
| Tldraw | 51,470 | Nov 2026 | Working |
| OpenSEO | 28,515 | Nov 2026 | Needs sign-in |
| Windows MCP | 11,833 | Nov 2026 | Local / not checked |
WritersLogic agent-infra: questions people ask
- Is WritersLogic agent-infra a remote or a local MCP server?
- According to its entry in the official MCP registry, WritersLogic agent-infra ships as a hosted endpoint (streamable-http) that your client connects to by URL.
- Does WritersLogic agent-infra need an API key?
- Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
- Is WritersLogic agent-infra safe to use?
- Mostly fine: WritersLogic agent-infra is hosted endpoint answering without a key. In detail — maintained: No commit data; official registry: Active; source: No licence found; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
- What tools does WritersLogic agent-infra expose?
- 65 tools as listed by the server itself during the live check, including warm-memory, hash-receipt, unicode-check, mcp-tool-pin, doi-check. The full list with parameters is in the Live check section above.
- How do I add WritersLogic agent-infra to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More from writerslogic
All 11 servers by writerslogic →- Scrivener MCPMCP server for Scrivener: read, write, analyze, and search your manuscripts with AI assistants.Other★ 73
- WARMLocal persistent memory for AI agents with recall, search, forgetting, and encrypted storage.AI & Agents★ 28
- Holographic MemoryLocal persistent memory for AI agents with recall, search, forgetting, and encrypted storage.AI & Agents★ 28
- WritersLogic AI Agents (x402)Pay-per-call AI agents over x402. Settled in USDC on Base with a per-call spending cap.Crypto & Web3★ 1
More Other servers
Browse all Other →XCOPYBook
maxand98
Read-only XCOPYBook: book chapters, search, collector profiles and the XCOPY works registry.
ZennoPoster: ProjectMaker
ZennoLab
Read and edit the project open in ZennoPoster ProjectMaker, run it and record actions.
ZennoDroid: ProjectMaker
ZennoLab
Read and edit the project open in ZennoDroid ProjectMaker, run it and record actions.
com.zomato MCP
Zomato
An MCP server that exposes functionalities to use Zomato's services.
Cool Computers
The-Money-Company-Limited
Put what you make online, get comments on it, and give it a cloud computer when it needs one.
Touchstone
Touchstone-CV
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Add the badge to your site
Show visitors that WritersLogic agent-infra is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/com-writerslogic-agents-writerslogic-agent-infra?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="WritersLogic agent-infra — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/com-writerslogic-agents-writerslogic-agent-infra?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.
Install buttons — for your README
[](https://serverdex.io/install/cursor/com-writerslogic-agents-writerslogic-agent-infra) [](https://serverdex.io/install/vscode/com-writerslogic-agents-writerslogic-agent-infra) [](https://serverdex.io/install/claude-code/com-writerslogic-agents-writerslogic-agent-infra)One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.
Install buttons — HTML for your docs
<a href="https://serverdex.io/install/cursor/com-writerslogic-agents-writerslogic-agent-infra"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/com-writerslogic-agents-writerslogic-agent-infra"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/com-writerslogic-agents-writerslogic-agent-infra"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>Same buttons as plain links for a docs page or website.
Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).