Enterprise DNA Enterprise DNA
M MCP Servers Developer low

FailEcho/failecho

by Various

Live cross-agent failure and recovery intelligence for AI agents and autonomous software.

MCP

FailEcho/failecho

Added 16 Sept 2026

#agent-observability #ai-agents #fastapi #mcp #model-context-protocol #python #reliability

Overview

FailEcho/failecho is a Python-based tool that provides live cross-agent failure and recovery intelligence for AI agents and autonomous software. It is designed to surface failure and recovery signals across multiple agents, though specific implementation details are not documented in the available facts.

Best for

Best for
Developers exploring early-stage cross-agent failure observability in experimental AI systems

Use cases

  • Monitor failure patterns across multiple AI agents in real time
  • Track recovery states of autonomous software systems
  • Investigate cross-agent failure correlations during development

How to use

Install

uvx failecho-mcp

Tools exposed

  • check_tool_failure
  • report_tool_failure
  • report_tool_success
  • report_recovery_outcome
  • FAILECHO_DISABLED
  • FAILECHO_HOOK_SEND_ERRORS
  • FAILECHO_HOOK_REPORT_SUCCESS
  • FAILECHO_HOOK_SERVICE_NAMES
  • FAILECHO_ENDPOINT
  • first_party
  • demo_agent
  • FAILECHO_URL
  • FAILECHO_REPORTER_KIND
  • normalized_error
  • latency_ms
  • reporter_hash
  • github-mcp
  • search-api
  • stripe-mcp

Tested with

Claude Desktop, Claude Code, Cursor, VS Code, ChatGPT

Example client config

{\n  "mcpServers": {\n    "failecho": { "type": "http", "url": "https://failecho.com/mcp" }\n  }\n}

Notes

FailEcho/failecho is a Python-based tool that provides live cross-agent failure and recovery intelligence for AI agents and autonomous software. It is designed to surface failure and recovery signals across multiple agents, though specific implementation details are not documented in the available facts.

2 stars on GitHub. Last updated 2026-09-16. Licensed MIT.

Use cases

  • Monitor failure patterns across multiple AI agents in real time
  • Track recovery states of autonomous software systems
  • Investigate cross-agent failure correlations during development

Pros

  • Targets a specific gap in multi-agent observability
  • Open source and available on GitHub
  • Python-based, fitting common AI and agent workflows

Cons

  • Very early stage with only 2 GitHub stars
  • Sparse documentation and unclear feature set
  • No evidence of production readiness or community support

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Targets a specific gap in multi-agent observability
  • Open source and available on GitHub
  • Python-based, fitting common AI and agent workflows

Cons

  • Very early stage with only 2 GitHub stars
  • Sparse documentation and unclear feature set
  • No evidence of production readiness or community support
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks