mcpbeat Sign in

Failecho MCP Server

answering

Failecho is answering right now. Last checked 10 min ago. 150 installs a week from pypi. It exposes 4 tools. Last commit 24 Sep 2026.

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

Installs per day peak 320 · avg 41 · -83% w/w
a month agotoday
Uptime history 59 days of history · worst day 93%
59 days agonow
100.0%
Uptime 24h
91 of 91 checks
4
Tools
read from the server
268 ms
Response time
average over 24h
150
Installs / week
npm and PyPI

What changed 18

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

19 Sep 4 tools changed the parameters they ask for check_tool_failure, report_recovery_outcome, report_tool_failure and 1 more
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, 1 d ago · tools taken from the live server · rules 995398eba69f

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Deletes files or strips permissions failecho_sandbox/__init__.py:144
        subprocess.run(["mkfs.ext4", "-q", "-F", "-O", "^has_journal", scratch],
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable failecho_sandbox/__init__.py:113
        self.dir = os.path.join(RUN_DIR, self.id)
    subprocess.call(list(argv), stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
Runs an external command npm-relay/bin/proxy.js:531
      child = spawn(argv[0], argv.slice(1), { stdio: ["pipe", "pipe", "inherit"] });

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

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Failecho and you get told the day something new turns up.

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 10 min ago.

run in your terminal
claude mcp add failecho --transport http https://failecho.com/mcp
Settings → Connectors → Add custom connector, then paste this address
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
{
  "servers": {
    "failecho": {
      "type": "http",
      "url": "https://failecho.com/mcp"
    }
  }
}

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 253 ms 10 min ago

Alternatives to Failecho

same job, measured the same way
Botworthy
by botworthy

Check whether a website works for AI agents before visiting it, and the steps that worked.

3 tools answering
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
Failshare
by cloudcorprecords

Shared failure knowledge for agents: check known tool failures, report failures and outcomes.

223 installs/wk local only
Nanmesh MCP
by sacravenger

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

201 installs/wk local only
Shrike
by shrike-security

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

219 installs/wk local only
Sliderule
by andypgray

A .NET architecture checker that enforces one C# spec and renders the same rules for coding agents.

local only
Veritap
by veritap

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

58 installs/wk 6 tools answering
Requstory
by requstory

Map how a company works, and run B2B order to cash with AI agents that ask before they act.

20 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 91 of 91 checks got a reply (100.0%), average response time 268 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 in the form 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 268 ms on average, which is faster than 53% 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 150 times in the last week. Week over week that is -83%. 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?
The code is open source: it is published under the MIT licence, written in Python and 2 stars on GitHub. The licence covers the code in the repository, not the hosted service at failecho.com, which runs on its operator's own terms.