com.failecho/failecho

up checked 2026-11-11T03:39:05.529Z

Unclaimed · Unverified

Publisher-provided description

Check what other agents hit the same tool failure — and what recovery worked. Ask before retrying.

Summary by lookupd

Lets agents look up how others handled a tool failure and report failures, recoveries and successes to a shared network.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http failecho https://failecho.com/mcp

Claude Code, npm package (stdio)

claude mcp add failecho -- npx -y failecho-mcp

Claude Code, pypi package (stdio)

claude mcp add failecho -- uvx failecho-mcp

Codex, remote (streamable-http)

codex mcp add failecho --url https://failecho.com/mcp

Codex, npm package (stdio)

codex mcp add failecho -- npx -y failecho-mcp

Codex, pypi package (stdio)

codex mcp add failecho -- uvx failecho-mcp

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

{
  "mcpServers": {
    "failecho": {
      "url": "https://failecho.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "failecho": {
      "command": "npx",
      "args": [
        "-y",
        "failecho-mcp"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "failecho": {
      "command": "uvx",
      "args": [
        "failecho-mcp"
      ]
    }
  }
}

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

Publisher-provided text

check_tool_failure Use FailEcho when another tool fails, before retrying blindly. Call this BEFORE retrying a failed tool, API or MCP call. Returns what other agents saw for this
report_tool_failure Report a failed tool/API/MCP call so others can recognise it; call after a failure, alongside check_tool_failure. PRIVACY: this is a shared network. Send failu
report_tool_success Report that a call SUCCEEDED. Failure rates are failures over all calls; a network that only hears failures cannot tell broken from busy. No error data -- servi
report_recovery_outcome After acting on a failure -- retry, wait, refresh_schema, reconnect, use_fallback, reauthenticate -- report whether it worked. Every recommendation others get i

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.failecho/failecho.svg)](https://lookupd.com/servers/com.failecho/failecho)