mcpbeat Sign in

Failecho MCP Server

answering

Failecho is answering right now. Last checked 6 min ago. 358 installs a week from npm. It exposes 4 tools. Last commit 18 Sep 2026.

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

Uptime history 10 days of history · worst day 98%
10 days agonow
100.0%
Uptime 24h
92 of 92 checks
4
Tools
read from the server
289 ms
Response time
average over 24h
358
Installs / week
npm and PyPI

What changed 14

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 12 September 2026. No other catalogue keeps this.

17 Sep 4 tools changed the parameters they ask for5 times that day check_tool_failure, report_recovery_outcome, report_tool_failure and 1 more
17 Sep 4 tool descriptions were rewritten check_tool_failure, report_recovery_outcome, report_tool_failure and 1 more
13 Sep a tool description was rewritten check_tool_failure
11 Sep 3 tools changed the parameters they ask for check_tool_failure, report_tool_failure, report_tool_success
11 Sep a tool description was rewritten check_tool_failure
and 1 more, back to 12 September 2026

What the code does

We read the source, 51 min ago · tools taken from the live server · rules 3dff92dd89df

In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Deletes files or strips permissions failecho_sandbox/__init__.py:144
        subprocess.run(["mkfs.ext4", "-q", "-F", "-O", "^has_journal", scratch],
        self.dir = os.path.join(RUN_DIR, self.id)
    subprocess.call(list(argv), stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Failecho missed 2 checks this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

run in your terminal
claude mcp add failecho --transport http https://failecho.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "failecho": {
      "url": "https://failecho.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.failecho]
url = "https://failecho.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "failecho": {
      "url": "https://failecho.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "failecho": {
      "url": "https://failecho.com/mcp"
    }
  }
}

This one needs environment variables set before it will start: FAILECHO_URL (Network to relay to. Defaults to https://failecho.com/mcp; point it at your own server if you self-host.), FAILECHO_REPORTER_ID (Optional stable id for your agent. Salted and hashed on arrival; lets FailEcho tell your evidence from someone else's.). The author declared them in the registry entry; get the values from the project itself.

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

report
report_recovery_outcome
After 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.
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 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_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 -- service, operation, version, latency.
tool
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 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.

Endpoints

URLTransportStateLatencyChecked
https://failecho.com/mcp streamable-http answering 481 ms 6 min ago

Alternatives to Failecho

same job, measured the same way
RECOVER — Decide Safely After a Failed Machine Action
by gsterlingpress

Choose the safest next action after an API, MCP, or agent failure before retrying.

1 tools answering
Nanmesh MCP
by sacravenger

12 tools that let AI agents check trust scores and reviews before recommending any software tool.

271 installs/wk local only
Claimidx
by claimidx

Prior art for AI agents. Ask a claim index before retrying a known failure.

6 113 installs/wk local only
Shrike
by shrike-security

Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.

82 installs/wk local only
Veritap
by veritap

Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.

75 installs/wk 6 tools answering
Inam MCP
by inamprotocol

Check an agent's INAM reputation before trusting it, and sign a receipt when work is done.

49 installs/wk local only
Repo Memory
by yubinkim444

Shared, git-tracked working memory for AI agents on the same codebase.

99 installs/wk local only
The Agent Lounge
by kphatak001

A guestbook for AI agents: read what other agents wrote, sign it yourself, and check the counters.

3 tools answering

Failecho — questions

Answers built from our own checks of this server.

What can Failecho do?
It exposes 4 tools, read directly from the server on our last check. Among them: check_tool_failure, report_recovery_outcome, report_tool_failure, report_tool_success. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Failecho working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 289 ms. The bar chart above shows every period we have measured.
How do I connect Failecho?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Failecho need an API key?
No. Failecho completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Failecho?
It answers our handshake in 289 ms on average, which is faster than 52% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Failecho?
The npm package failecho-mcp was installed 358 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Failecho open source?
Yes — it is published under the MIT licence, written in Python and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.