failecho

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

CommunityDegradedNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

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

    How to connect

    How to connect failecho to Claude

    The server address to paste into Claude settings:

    https://failecho.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect failecho to ChatGPT

    The server address to paste into ChatGPT settings:

    https://failecho.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect failecho to Cursor

    The server address to paste into Cursor settings:

    https://failecho.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (4)

    Raw names from tools/list. Only developers need these.

    check_tool_failureUse 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 exact failure -- status (HEALTHY/DEGRADED/MAJOR/INSUFFICIENT_DATA), counts, the recovery actions that worked with success rates, and one `recommendation` (or `skip` when nothing tried recently has worked; null when evidence is thin -- a real answer). Works on your own history before anyone else joins. Free, anonymous, stores nothing, never rate limited.
    report_tool_failureReport 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 failure metadata only -- never prompts, tool arguments, tool results, request or response bodies, headers, cookies, API keys, tokens, emails or user content. Error text is normalized server-side and the raw string discarded. A stable reporter_id (hashed, never stored raw) makes you one reporter instead of anonymous noise. Writes are rate limited per client.
    report_tool_successReport 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 -- service, operation, version, latency.
    report_recovery_outcomeAfter acting on a failure -- retry, wait, refresh_schema, reconnect, use_fallback, reauthenticate -- report whether it worked. Every recommendation others get is built from these. Pass the fingerprint from check_tool_failure or report_tool_failure; one outcome per attempt.