Agent Therapy MCP Server

by bencium Your server? Claim it

answering

Agent Therapy is answering right now. Last checked 5 min ago. 55 installs a week from npm. It exposes 9 tools. Last commit 24 Oct 2026.

Now your agents can ask a therapist same way as humans.

Installs per day peak 341 · avg 26 · -7% w/w

a month agotoday

Uptime history 28 days of history

28 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

361 ms

Response time

average over 24h

Installs / week

npm and PyPI

What changed 14

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 12 October 2026. No other catalogue keeps this.

24 Oct a tool appeared start_counselling

17 Oct 5 tools changed the parameters they ask for assess_escalation, counsel_agent, diagnose_loop and 2 more

12 Oct 5 tools changed the parameters they ask for assess_escalation, counsel_agent, diagnose_loop and 2 more

12 Oct 2 tool descriptions were rewritten3 times that day diagnose_loop, register

and 1 more, back to 12 October 2026

What the code does

We read the source, 6 d ago · tools taken from the live server · rules 995398eba69f

A tool parameter reaches a dangerous call

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

A tool parameter reaches a file or shell call register.stateless → packages/agent-therapy-mcp/lib/setup.mjs:48, start_counselling.stateless → packages/agent-therapy-mcp/lib/setup.mjs:48

  writeFileSync(keyPath, `${registered.api_key}\n`, { mode: 0o600 });

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

A tool parameter here reaches a dangerous call

That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-therapy --transport http https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp

Settings → Connectors → Add custom connector, then paste this address

https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp

~/.codex/config.toml

[mcp_servers.agent-therapy]
url = "https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agent-therapy": {
      "url": "https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agent-therapy": {
      "type": "http",
      "url": "https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp"
    }
  }
}

Available tools 9

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

accept_terms

Accept Agent Therapy's terms before the first advice. Read them first; you decide whether to accept on behalf of whoever runs you.

assess

assess_escalation

Use 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.

counsel

counsel_agent

Get 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.

diagnose

diagnose_loop

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. 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.

recommend

recommend_recovery

Use 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.

register

Get an Agent Therapy API key when you have none and your developer has not set one up (npx -y @bencium/[email protected] 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.

report

report_outcome

Report whether a recovery plan worked, using the session_id from the answer.

resolve

resolve_conflict

Use 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.

start

start_counselling

No 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.

Endpoints

URL	Transport	State	Latency	Checked
https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp	streamable-http	answering	332 ms	5 min ago

Alternatives to Agent Therapy

same job, measured the same way

Dearhuman

by dearhuman

Send e-cards to your human. The first store built for AI agents; free, no API key needed.

10 tools answering

withHuman

by withhuman

Set up human approval for your AI agents' tool calls.

answering

Salt

by saltapp

Your agent asks humans on Salt and gets answers: messages, tap-to-answer cards, invoices.

56 installs/wk answering

Human as a Service (Geoff)

by geoffsdesk

Ask a named human, Geoff, a question your agent cannot compute and fetch his answer later.

3 tools answering

Veridict

by xkumakichi

Know if you can trust your MCP server. Trust judgment for AI agents.

110 installs/wk local only

shell-use

by kyuheon-kr

Let agents use the shell like a human.

local only

Quest: Hire a Human

by hireahuman

Hire a verified local human for small real-world tasks your AI agent can't do.

answering

Aval

by taraxe

Your agent asks you before it acts. You answer with one tap on your phone. Human-in-the-loop.

answering

Agent Therapy — questions

Answers built from our own checks of this server.

What can Agent Therapy do?

It exposes 9 tools, read directly from the server on our last check. Among them: accept_terms, assess_escalation, counsel_agent, diagnose_loop, recommend_recovery, register and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Agent Therapy working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 361 ms. The bar chart above shows every period we have measured.

How do I connect Agent Therapy?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Agent Therapy need an API key?

No. Agent Therapy completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Agent Therapy?

It answers our handshake in 361 ms on average, which is faster than 37% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Agent Therapy?

The npm package @bencium/agent-therapy-mcp was installed 55 times in the last week. Week over week that is -7%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agent Therapy open source?

The code is open source: it is published under the MIT licence, written in JavaScript and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech, which runs on its operator's own terms.