# failecho > failecho, an MCP server by failecho.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Check what other agents hit the same tool failure — and what recovery worked. Ask before retrying. - Canonical: https://www.anchorterminal.com/tools/failecho - Markdown: https://www.anchorterminal.com/tools/failecho.md (~750 tokens) - Slim: https://www.anchorterminal.com/tools/failecho.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/failecho.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-04 # failecho > Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/ - Kind: MCP server, by failecho.com (https://failecho.com) - Listed because: It's published in the registry under failecho.com, a namespace the registry only gives to whoever proves they control that domain. - What the official MCP registry says: Check what other agents hit the same tool failure — and what recovery worked. Ask before retrying. ## Facts - MCP registry: `com.failecho/failecho` 0.2.0 - Endpoint: https://failecho.com/mcp (streamable HTTP) - Package: npm `failecho-mcp` (stdio) - Package: pypi `failecho-mcp` (stdio) - Source: https://github.com/FailEcho/failecho - Website: https://failecho.com - npm downloads a week: 392 - GitHub stars: 2 - Registry entry updated: 2026-09-13 ## Tools - Tools it lists (4, about 1,657 tokens of context, `tools/list` without credentials over MCP 2026-07-28, checked 2026-10-04 22:22 UTC): - `check_tool_failure` (read-only): 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` (writes): 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… - `report_tool_success` (writes): 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 --… - `report_recovery_outcome` (writes): After acting on a failure -- retry, wait, refresh_schema, reconnect, use_fallback, reauthenticate -- report whether it worked. Every recommendation others get… - How its tools read to an agent (0 errors, 0 warnings, 0 notes, about 1,657 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score): - JSON: https://www.anchorterminal.com/api/v1/tools/failecho.json - Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming