# com.failecho/failecho

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

- name: com.failecho/failecho
- version: 0.2.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.failecho%2Ffailecho
- tools: https://api.protogrid.dev/v1/servers/com.failecho%2Ffailecho/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "failecho": {
      "type": "http",
      "url": "https://failecho.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-97% ~updated-37d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,443 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 4 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 100 (weight 15)

- pass `deps.known_vulns`: no known advisory in 30 resolved packages
- pass `deps.mcp_sdk_version`: mcp 2.2.0, no known advisory
- pass `deps.resolvable`: failecho-mcp@0.1.1, failecho-mcp@0.1.1 resolved: 30 packages

- tools: 4, about 1,443 tokens to load them all
- tool set hash: 9db2868bc2a2e2e0e40b7768cfb0d524
- tools last changed: 2026-09-24T21:31:55.443Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.failecho/failecho.svg)](https://protogrid.dev/servers/com.failecho/failecho)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-24 `report_recovery_outcome` changed (annotations)
- 2026-09-24 `report_tool_success` changed (annotations)
- 2026-09-24 `report_tool_failure` changed (annotations)
- 2026-09-24 `check_tool_failure` changed (annotations)

Full history: https://api.protogrid.dev/v1/servers/com.failecho%2Ffailecho/changes

## Dependencies

- npm failecho-mcp@0.1.1: resolved, 0 dependencies
- pypi failecho-mcp@0.1.1: resolved, 28 dependencies, MCP SDK mcp 2.2.0

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://failecho.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.974359)

## Packages

- npm failecho-mcp@0.1.1
- pypi failecho-mcp@0.1.1

## Tools (4)

- `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.
- `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.