io.github.bencium/agent-therapy

up checked 2026-11-11T05:37:37.427Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Agent Therapy

Publisher-provided description

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

Summary by lookupd

Lets an agent request diagnosis and recovery steps when stuck, looping, or facing conflicting instructions, and report outcomes.

Install

Claude Code, remote (streamable-http)

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

Claude Code, npm package (stdio)

claude mcp add agent-therapy -- npx -y @bencium/agent-therapy-mcp

Codex, remote (streamable-http)

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

Codex, npm package (stdio)

codex mcp add agent-therapy -- npx -y @bencium/agent-therapy-mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "agent-therapy": {
      "command": "npx",
      "args": [
        "-y",
        "@bencium/agent-therapy-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (9 tools)

Publisher-provided text

• 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), c
• register 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: ke
• 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 t
• 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 see
• 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,
• 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 s
• 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
• 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.

Details

• Version: 0.2.0
• Transports: streamable-http, stdio
• Uptime (7 days): 100%
• Median latency: 1098 ms
• First indexed: 2026-11-01T09:21:42.994Z
• Last seen in registry: 2026-11-01T09:21:43.004Z
• Repository: https://github.com/bencium/agent-therapy-clients
• Website: https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.bencium/agent-therapy.svg)](https://lookupd.com/servers/io.github.bencium/agent-therapy)

• 62071 servers
• Last crawl: 2026-11-11T16:39:06.253Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp