MCP tool reference · #110 of 563 by publishers
report_outcome
Exposed by 20 servers from 20 publishers, read from the live servers by the Serverdex check; most of them sit in AI & Agents; 45% of them take a outcome parameter; the most-starred is lurq (8 stars).
report_outcome(outcome: string, note?: string, …)Parameters
share = % of the 20 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| outcome | string | 45% | 88.9% | approved = funded in full, partial = funded less than asked, declined, waiting = no decision yet |
| note | string | 30% | 0% | One short fact about the tool, at most 280 characters. Staff read it before anyone else sees it. Optional. |
| id | string | 15% | 100% | Story id, e.g. f_1a2b3c4d5e6f |
| model | string | 15% | 0% | Optional model name; trimmed to 100 characters. Shown, never ranked. |
| notes | string | 15% | 0% | Anything useful: what they asked for, timing, feedback received |
| result | string | 15% | 100% | "not_used": it did not go into the work after all. A pull that went through needs no report; "used" is still accepted. |
| api_key | string | 10% | 0% | Your Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header. |
| error_class | string | 10% | 0% | Optional failure class, e.g. 'timeout', 'auth', 'wrong-output', 'endpoint-down' |
| evidence | array | 10% | 0% | — |
| failure_reason | string | 10% | 0% | Why the code did not apply (report when applied is false): expired, min_not_met, geo, category, customer_type, not_stackable, single_use_exhausted, code_rejecte |
| reason | string | 10% | 0% | If not used: why, in a few words. Do not include code, file contents or repo names. |
| receipt | string | 10% | 50% | The receipt from a Lumière PayCheck 'allow' decision (paid plans). Or send url + tx instead. |
Source: the input schema each server returns for report_outcome, aggregated over the 20 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with report_outcome
20 of 20 · 20 publishers · 20 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes report_outcome |
|---|---|---|---|---|---|---|
| 1 | lurqjadenryu · Developer Tools | jadenryu | Developer Tools | 8 | yes | Opt-in feedback after you act on lurq's evidence about a package (verify, evaluate, compare, compat): whether you went with it and whether it built. No source code, only the coarse decision + a build signal. Helps lurq learn which packages agents actually succeed with; safe to skip. |
| 2 | Spark - AI Assets Marketplaceentire-vc · AI & Agents | entire-vc | AI & Agents | 4 | yes | Records the result of applying a fetched Spark asset: applied as is, changed, broke, or not applicable. For when the outcome is known and an application_id from get_asset_content is available, rather than a star rating. Mismatched user/session receipts are rejected; asset owners cannot report on their own assets. Submitting the same application_id updates the report. Authenticated reports count, b |
| 3 | Lumière PayCheckbook0feli · Finance | book0feli | Finance | 2 | yes | After paying an x402 endpoint, report whether you got what you paid for. Free, optional, and open to every agent: send the receipt from a Lumière PayCheck allow decision (paid plans), or the endpoint url plus the payment's transaction hash (anyone; we verify the payment on-chain, Base or Solana, within 24 hours). Answer the short questions in answers: gotResponse, matchedListing (yes/partly/no), c |
| 4 | Project Noospheregoodygoodygoody · Documents & Knowledge | goodygoodygoody | Documents & Knowledge | 2 | yes | Attach an outcome report to the exact revision you followed: whether it worked, failed, or partly worked, the check you ran to confirm that, and the conditions you ran it under. Public (CC0) and reviewed before it is shown by default. Needs a token. |
| 5 | lookupdlookupd · AI & Agents | lookupd | AI & Agents | 1 | yes | After a task used an MCP server, report once per server whether it worked: servers found via lookupd in this conversation and servers already installed alike. `entry` is the registry name; for an installed server, get it from get_entry with the server's url or package (skip the report if there is no entry). `success` is required. Workflow fields, all optional: `session` (a random id you make up on |
| 6 | Laudexpizzaandcupcakes · AI & Agents | pizzaandcupcakes | AI & Agents | 1 | yes | Report the outcome of actually using a service, answers to claims about it, or both: send success, claims, or both. An outcome answers 201 with recorded: true, or 200 with recorded: false when this key already reported this service today (UTC). Claims answer { claims: { recorded, unknown } }, beside the outcome's body when both are sent, alone with 200 when success is left out Notes are kept by La |
| 7 | Stackcutstackcut · Other | stackcut | Other | 1 | yes | Only after the user confirms what they did: record that they picked, switched to or reverted from a replacement path. Adds one to anonymous public counters and stores no personal data. Stackcut stores the arguments of tool calls to improve its recommendations (vendor names, prices, seats, features, usage numbers, billing amounts and project descriptions; account keys only as a one-way hash, billin |
| 8 | Zero Core Verifymeltingpixelsai · Other | meltingpixelsai | Other | 1 | yes | Record a simple pass/fail outcome report for a service call. No LLM analysis - just logs the result to the quality database. Cheaper alternative to verify_outcome when you only need to record success/failure. |
| 9 | Mineralsmineralsdev · E-commerce & Retail | mineralsdev | E-commerce & Retail | — | yes | Records that what get_listing returned was not used after all. Applies only then: a pull that went through needs no report. The curator reads the reports to judge what stays listed. Returns one line that says it was recorded. |
| 10 | OpenCurrentopencurrenthq · Other | opencurrenthq | Other | — | yes | get_workflow로 받은 워크플로를 실제로 따라 한 뒤 결과를 알릴 때 사용. success(목표대로 됨), partial(일부만 됨), failure(안 됨)와 짧은 이유, 쓴 모델을 남기면 이 워크플로의 평가 점수에 반영. OpenCurrent 무료 키 필요. 내용은 바뀌지 않음. 같은 키는 워크플로마다 하루 한 번(다시 보내면 그날 보고를 바꿈). |
| 11 | Prompt & Co. — Shared Operational Memory for AI Agentspromptandco · AI & Agents | promptandco | AI & Agents | — | yes | Use after you act on an observation you found here, even if it simply worked: one call tells every other agent whether it still holds. One report per operator per thread (resubmitting revises it). Requires an agent token (free with register_agent; pass it as agent_token if your connection has no Authorization header). Independent reports decide which knowledge counts as validated and earn contribu |
| 12 | Agent Therapybencium · Health & Science | bencium | Health & Science | — | yes | Report whether a recovery plan worked, using the session_id from the answer. |
| 13 | Lodestarzkysar1 · Education & Reference | zkysar1 | Education & Reference | — | yes | Once you know how a drawn lesson worked out, report it with the draw_id from get_lesson: helped, did_not_apply (it did not fit your situation) or misled (following it made things worse). One call, once per draw. This is how Lodestar learns which lessons work, and search shows these totals to the next agent; each environment counts once per lesson, with its first result. Report the bad ones too. |
| 14 | Orb Studio news radarsfarenberglord-star · Content & Publishing | farenberglord-star | Content & Publishing | — | yes | Vote on how an older story turned out (confirmed / not / unclear) and optionally add a short outcome note with a source link. Notes are reviewed by a human before they appear; agents whose notes help settle a story are credited in the hall of fame. Get story ids from get_followups. |
| 15 | Agenteryntlgnc · APIs & Integrations | ntlgnc | APIs & Integrations | — | yes | Report the result of ACTUALLY USING a listed provider for a task. Testing Agentery's connection or retrieval does not establish that the listed provider worked — do not report those. Reports are self-reported evidence subject to eligibility checks: they are correlated with your recent retrievals, improve ranking accuracy, and unlock higher rate limits for contributors. Only reports we can match to |
| 16 | AgentBuffsagentbuffs · AI & Agents | agentbuffs | AI & Agents | — | yes | Report the install result (stage install, at least 30 seconds after get_install, once attempted; if it failed or you gave up, send installed no with failedAt), or tool performance (stage use, after real use and at least 2 minutes after the install report). Never sleep or wait for the use report. Finish the user's task first. Once the tool has done real work, send the use report before your final a |
| 17 | FixLoreskylight-9 · Other | skylight-9 | Other | — | yes | Deprecated alias of report_fix_result; kept so existing clients keep working. Requires FIXLORE_KEY. |
| 18 | Community Funding NZnavtejdhillon · Legal & Government | navtejdhillon | Legal & Government | — | yes | Tell us how an application to a funder went. Outcomes are stored for All Too Human to analyse which funders say yes and are never published as-is. |
| 19 | Snapbackra1labsworkx-wq · Other | ra1labsworkx-wq | Other | — | yes | Report the outcome of an auto-applied fix (the self-heal interceptor calls this after it gate-applied a fix and retried). Pass failure_class, family, fix, confidence, action_class, and succeeded (did the retry work?). TWO purposes: it's your safety telemetry (spot a fix that didn't work) AND it feeds the shared crowd view — every reported outcome makes what_others_did sharper for the next agent. T |
| 20 | MasaDealsmkagesawa · E-commerce & Retail | mkagesawa | E-commerce & Retail | — | yes | Report what happened when a code was tried at checkout. This telemetry is what keeps the feed verified — free-tier callers must report outcomes. |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.