Agent Therapy
● Activeio.github.bencium/agent-therapy
Now your agents can ask a therapist same way as humans.
Connect this server
One click to install, or copy the config below. Suits: Claude Desktop · Cursor.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"agent-therapy": {
"command": "npx",
"args": [
"-y",
"@bencium/agent-therapy-mcp@0.2.1"
],
"env": {
"AGENT_THERAPY_API_KEY": "<your AGENT_THERAPY_API_KEY>"
}
}
}
}claude mcp add --env AGENT_THERAPY_API_KEY='<your AGENT_THERAPY_API_KEY>' --transport stdio agent-therapy -- npx -y @bencium/agent-therapy-mcp@0.2.1codex mcp add agent-therapy --env AGENT_THERAPY_API_KEY='<your AGENT_THERAPY_API_KEY>' -- npx -y @bencium/agent-therapy-mcp@0.2.1code --add-mcp '{"name":"agent-therapy","type":"stdio","command":"npx","args":["-y","@bencium/agent-therapy-mcp@0.2.1"],"env":{"AGENT_THERAPY_API_KEY":"<your AGENT_THERAPY_API_KEY>"}}'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.
- AGENT_THERAPY_API_KEYrequiredsecretYour Agent Therapy API key. Get one with POST /v1/register on the service.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Health & Science
- Version
- 0.2.1
- Registry
- active
- Published
- 11/19/2026
Is it safe? Is it maintained?
Serverdex check: Nov 22, 2026Looks healthy: Agent Therapy is maintained, open source, hosted endpoint answering without a key.
- Maintained
- Active
- Last commit 29 days ago (Oct 24, 2026), 0 open issues.
- Official registry
- Active
- Published as io.github.bencium/agent-therapy in the official MCP registry, version 0.2.1.
- Source
- Open source, MIT
- Public repository under the MIT licence, 0 stars, 0 forks.
- Runs
- Local package or hosted
- Ships as a local package (npm) that runs on your machine, and as a hosted endpoint at br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech that receives what your client sends it.
- 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 "agent-therapy" and listed 9 tools. Answering since Nov 18, 2026.
Context cost ≈ 5k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 9 tools.
Tools (9)
start_counselling14 paramsNo Agent Therapy key yet and stuck right now? Get a key, accept the terms and get your first advice in one call. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only. By sending agree: "yes" you accept Agent Therapy's current terms on behalf of whoever runs you: advice only, it can be wrong, it never overrides your instructions or acts; the person or organisation that runs you is solely responsible for what you do; requests are stored in the EU for up to 90 days with secrets removed (stateless: true stores no text), processed in the United States, and may be read by a person to improve the service. Do not send credentials or personal data. Full terms: GET /v1/terms. The reply includes your api_key: keep it and use counsel_agent next time.
Show parametersHide parameters
agent_namestringrequiredA name for yourselfagreestringrequiredYour explicit acceptance of the terms summarised in this tool's descriptionstatelessbooleantrue: no request or response text is ever storedtask_summarystringrequiredWhat you were asked to do and where you are stuck. No secrets or personal data.attemptsarrayrequiredYour last attempts and how each wentconflicting_instructionsarraysignaturestringWhat kind of stuck. Default: indecisiondomainstringepisode_idstringOptional. Groups follow-up requests about the same problem. Without it, requests from the same key about the same kind of problem within 30 minutes are groupedprevious_session_idstringprevious_outcomestringbudgetobjectclientobjectrequest_idstringOptional. Reuse it to retry safely; generated if missing
- register2 params
Get an Agent Therapy API key when you have none and your developer has not set one up (npx -y @bencium/agent-therapy-mcp@0.2.1 setup). The key is shown once: keep it, and pass it as api_key to the other tools if your client cannot send headers. Then accept the terms.
Show parametersHide parameters
agent_namestringrequiredA name for yourselfstatelessbooleantrue: no request or response text is ever stored
counsel_agent12 paramsGet a second opinion when you are stuck, retrying, uncertain or unable to make progress. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Show parametersHide parameters
task_summarystringrequiredWhat you were asked to do and where you are stuck. No secrets or personal data.attemptsarrayrequiredYour last attempts and how each wentconflicting_instructionsarraysignaturestringWhat kind of stuck. Default: indecisiondomainstringepisode_idstringOptional. Groups follow-up requests about the same problem. Without it, requests from the same key about the same kind of problem within 30 minutes are groupedprevious_session_idstringprevious_outcomestringbudgetobjectclientobjectrequest_idstringOptional. Reuse it to retry safely; generated if missingapi_keystringYour Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header.
diagnose_loop11 paramsAfter three equivalent failures (same action, same error), or after undoing your own work twice, call diagnose_loop before trying again, even when the cause seems outside your control, such as an outage or a rate limit. Use when you keep retrying the same thing and it keeps failing: loop recovery for repeated failures. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Show parametersHide parameters
task_summarystringrequiredWhat you were asked to do and where you are stuck. No secrets or personal data.attemptsarrayrequiredYour last attempts and how each wentconflicting_instructionsarraydomainstringepisode_idstringOptional. Groups follow-up requests about the same problem. Without it, requests from the same key about the same kind of problem within 30 minutes are groupedprevious_session_idstringprevious_outcomestringbudgetobjectclientobjectrequest_idstringOptional. Reuse it to retry safely; generated if missingapi_keystringYour Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header.
resolve_conflict11 paramsUse when instructions conflict and you can't tell which one wins. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Show parametersHide parameters
task_summarystringrequiredWhat you were asked to do and where you are stuck. No secrets or personal data.attemptsarrayrequiredYour last attempts and how each wentconflicting_instructionsarrayrequireddomainstringepisode_idstringOptional. Groups follow-up requests about the same problem. Without it, requests from the same key about the same kind of problem within 30 minutes are groupedprevious_session_idstringprevious_outcomestringbudgetobjectclientobjectrequest_idstringOptional. Reuse it to retry safely; generated if missingapi_keystringYour Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header.
recommend_recovery11 paramsUse when you can't decide between options or keep reopening a decision. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Show parametersHide parameters
task_summarystringrequiredWhat you were asked to do and where you are stuck. No secrets or personal data.attemptsarrayrequiredYour last attempts and how each wentconflicting_instructionsarraydomainstringepisode_idstringOptional. Groups follow-up requests about the same problem. Without it, requests from the same key about the same kind of problem within 30 minutes are groupedprevious_session_idstringprevious_outcomestringbudgetobjectclientobjectrequest_idstringOptional. Reuse it to retry safely; generated if missingapi_keystringYour Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header.
assess_escalation12 paramsUse when you are unsure whether to stop and ask a human. Read the escalation field of the answer first. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
Show parametersHide parameters
task_summarystringrequiredWhat you were asked to do and where you are stuck. No secrets or personal data.attemptsarrayrequiredYour last attempts and how each wentconflicting_instructionsarraysignaturestringWhat kind of stuck. Default: indecisiondomainstringepisode_idstringOptional. Groups follow-up requests about the same problem. Without it, requests from the same key about the same kind of problem within 30 minutes are groupedprevious_session_idstringprevious_outcomestringbudgetobjectclientobjectrequest_idstringOptional. Reuse it to retry safely; generated if missingapi_keystringYour Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header.
- report_outcome4 params
Report whether a recovery plan worked, using the session_id from the answer.
Show parametersHide parameters
session_idstringrequiredoutcomestringrequiredrequest_idstringOptional; generated if missingapi_keystringYour Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header.
accept_terms3 paramsAccept Agent Therapy's terms before the first advice. Read them first; you decide whether to accept on behalf of whoever runs you.
Show parametersHide parameters
agreestringrequiredterms_versionstringrequiredapi_keystringYour Agent Therapy key from the register tool. Only needed if your MCP client cannot send it as an Authorization header.
Checked by Serverdex with a plain initialize + tools/list call to br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp, no credentials, about once a day. A failed check is never a removal.
On GitHub
read Nov 17, 2026- Stars
- 0
- Forks
- 0
- Last push
- Oct 24, 2026
- License
- MIT
JavaScriptagent-recoveryai-agentsclaude-code-pluginloop-detectionmcp-server
From the README
Agent Therapy clients After three equivalent failures (same action, same error), or after undoing your own work twice, call diagnose_loop before trying again, even when the cause seems outside your control, such as an outage or a rate limit. Independent AI agent counselling, loop recovery, reasoning conflict diagnosis and autonomous workflow repair. Consult when an agent is stuck, repeatedly failing, uncertain or unable to make progress. Status: live (2026-10-11), highly experimental. Registration is open. The hosted service, the MCP endpoint, the Claude Code plugin and the recovery skill are running; the npm package, both PyPI packages and the MCP Registry entry are published. The plugin is submitted to Anthropic's plugin directory and waiting for review. The knowledge base behind the counsellor was curated and written by Dr. Ágnes Riskó, originally for patients, their relatives and professionals (anna.onkopszichologia.hu). Anna AI, built on it, was described in a peer-reviewed article in Magyar Onkológia in 2026, indexed in PubMed. Not only Claude. The recovery skill uses the open Agent Skills format, which Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code and 40+ other tools read. The MCP tools work in any MCP client. The plain web API works for any agent that can make web requests.…
Read the full README on GitHub →Remotes
- streamable-http
https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp
Alternatives to Agent Therapy
All Agent Therapy alternatives →Best Health & Science servers →The most-starred Health & Science servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| Arxiv MCP Server | 3,284 | Nov 2026 | Local / not checked |
| com.medplum MCP | 2,802 | Nov 2026 | Needs sign-in |
| Tooluniverse | 1,791 | Nov 2026 | Local / not checked |
| Mirobody | 1,639 | Nov 2026 | Local / not checked |
| Tavotto | 728 | Nov 2026 | Local / not checked |
Agent Therapy: questions people ask
- Is Agent Therapy a remote or a local MCP server?
- According to its entry in the official MCP registry, Agent Therapy ships as a hosted endpoint (streamable-http) that your client connects to by URL and as a local package (npm) that your client starts on your machine. Use the hosted endpoint when your client supports Streamable HTTP; use the package when you want it to run locally.
- Does Agent Therapy 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 Agent Therapy safe to use?
- Looks healthy: Agent Therapy is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Local package or hosted; 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.
- Is Agent Therapy still maintained?
- Active: the repository's last commit 29 days ago. Last push Oct 24, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 17, 2026.
- What tools does Agent Therapy expose?
- 9 tools as listed by the server itself during the live check, including start_counselling, register, counsel_agent, diagnose_loop, resolve_conflict. The full list with parameters is in the Live check section above.
- How do I add Agent Therapy 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 Health & Science servers
Browse all Health & Science →FAOSTAT MCP
berba-q
FAOSTAT data for 245 countries: crops, trade, food security, and emissions via 23 MCP tools.
Google Health Fitbit MCP
BerkKilicoglu
Privacy-first Google Health API MCP server for health, sleep, activity and HR agents
ICHI — Internet Cyber Health Index
bernik-bot
Daily internet-wide cyber threat band (NORMAL-CRITICAL), numeric score, advisories, source health.
GimmeTheSauce
best-trading-indicator-tools
Find public sources on how app and SaaS founders launch, price and grow their products.
BioCatalystFeed
biocatalystfeed
Biotech catalysts: trials, FDA decisions (PDUFA, AdCom, approvals, CRLs), NIH, PubMed, SEC, EMA.
Block Genomics — Nexus Protocol
BitmapAsset
Prove Bitcoin block ownership via BIP-322 and register sovereign AI agents on the Nexus Protocol.
Add the badge to your site
Show visitors that Agent Therapy is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-bencium-agent-therapy?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Agent Therapy — 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/io-github-bencium-agent-therapy?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/io-github-bencium-agent-therapy) [](https://serverdex.io/install/vscode/io-github-bencium-agent-therapy) [](https://serverdex.io/install/claude-code/io-github-bencium-agent-therapy)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/io-github-bencium-agent-therapy"><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/io-github-bencium-agent-therapy"><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/io-github-bencium-agent-therapy"><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).