Agent Therapy

Last 30 days

Uptime

100%

Response time

258 ms typical, 258 ms slowest 5%

Last check

5 h ago

Next check

in 1 h

How to call it

Add it to any MCP client that supports remote servers.

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

8 tools

• register

  Get an Agent Therapy API key when you have none. 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.

• 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_loop

  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.

• 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.

• 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.

• 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.

• report_outcome

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

• 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.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks