# com.failecho/failecho (remote · failecho.com)

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

- Trust score: 71/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-22

## Components

- remote · `failecho.com`: 71/100 (this document), [markdown](https://verifymcp.io/servers/com-failecho-failecho/failecho.md), [page](https://verifymcp.io/servers/com-failecho-failecho/failecho)
- npm · `failecho-mcp`: 40/100, [markdown](https://verifymcp.io/servers/com-failecho-failecho/failecho-mcp.md), [page](https://verifymcp.io/servers/com-failecho-failecho/failecho-mcp)
- pypi · `failecho-mcp`: 48/100, [markdown](https://verifymcp.io/servers/com-failecho-failecho/failecho-mcp-2.md), [page](https://verifymcp.io/servers/com-failecho-failecho/failecho-mcp-2)

## Channel facts

- Endpoint: `https://failecho.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-22.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1151 tokens (~287/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the com.failecho/failecho MCP server?

com.failecho/failecho is a hosted endpoint at https://failecho.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-failecho-failecho 'https://failecho.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-failecho-failecho": {
      "url": "https://failecho.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-failecho-failecho]
url = "https://failecho.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-failecho-failecho": {
      "type": "remote",
      "url": "https://failecho.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-failecho-failecho --url 'https://failecho.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-failecho-failecho:
    url: "https://failecho.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-failecho-failecho": {
      "Transport": "http",
      "Url": "https://failecho.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-failecho-failecho -t streamable-http -u 'https://failecho.com/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-22 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-20 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 69, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “report_recovery_outcome” rewrote its description, which is the text the model reads
- [security] Tool “report_tool_failure” rewrote its description, which is the text the model reads
- [security] Tool “report_tool_success” rewrote its description, which is the text the model reads
- [security] Tool “check_tool_failure” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 454 → 278
- [cosmetic] “check_tool_failure” added an optional parameter “verbose”
- [cosmetic] “check_tool_failure” reworded the description of “error_message”
- [cosmetic] “check_tool_failure” reworded the description of “error_type”
- [cosmetic] “check_tool_failure” reworded the description of “operation”
- [cosmetic] “check_tool_failure” reworded the description of “reporter_id”
- [cosmetic] “check_tool_failure” reworded the description of “schema_hash”
- [cosmetic] “check_tool_failure” reworded the description of “service”
- [cosmetic] “check_tool_failure” reworded the description of “version”
- [cosmetic] “report_recovery_outcome” reworded the description of “action”
- [cosmetic] “report_recovery_outcome” reworded the description of “fingerprint”
- [cosmetic] “report_tool_failure” reworded the description of “operation”
- [cosmetic] “report_tool_failure” reworded the description of “service”
- [cosmetic] “report_tool_success” reworded the description of “operation”
- [cosmetic] “report_tool_success” reworded the description of “service”
- [cosmetic] “check_tool_failure” reworded the description of “error_code”

### 2026-09-17 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 66, +2)

- [security improvement] HSTS header: fail → pass

### 2026-09-13 (score 64, +1)

- [security] Tool “check_tool_failure” rewrote its description, which is the text the model reads

### 2026-09-12 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “check_tool_failure” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 361 → 437
- [cosmetic] “check_tool_failure” reworded the description of “operation”
- [cosmetic] “report_tool_success” reworded the description of “service”
- [cosmetic] “report_tool_success” reworded the description of “operation”
- [cosmetic] “report_tool_failure” reworded the description of “service”
- [cosmetic] “report_tool_failure” reworded the description of “operation”
- [cosmetic] “check_tool_failure” reworded the description of “service”

## MCP tools (4)

### `check_tool_failure` (~357 tokens)

Check what the network knows about a 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.

Input parameters:

- `error_code` (string): Code, e.g. '422', 'ECONNRESET'.
- `error_message` (string): The error text only; normalized server-side, not stored by this call.
- `error_type` (string): Failure class, e.g. 'validation_error', 'timeout', 'rate_limit', 'auth_error'.
- `operation` (string, required): The tool or endpoint as the server names it, e.g. 'create_issue', not 'mcp__github__create_issue'.
- `reporter_id` (string): Optional stable agent id; hashed, never stored raw. Lets from_other_agents be answered.
- `schema_hash` (string): Short hash of the tool schema you used (separates 'API broke' from 'schema stale').
- `service` (string, required): The MCP server's own name (serverInfo.name) or the API host, e.g. 'api.github.com'. Not your client's local alias.
- `verbose` (boolean): Full record (timestamps, rates, effective counts, every action). Default: the compact answer.
- `version` (string): Service/tool version, if known.

### `report_tool_failure` (~304 tokens)

Report a failed tool call to the network

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.

Input parameters:

- `error_code` (string): Protocol/vendor code, e.g. '422'.
- `error_message` (string): Error text. Normalized before storage; no secrets please.
- `error_type` (string): Short failure class, e.g. 'validation_error'.
- `latency_ms` (integer): Observed call latency in milliseconds.
- `operation` (string, required): The tool or endpoint as the server names it, e.g. 'create_issue', not 'mcp__github__create_issue'.
- `reporter_id` (string): Optional stable identifier for your agent. Salted and hashed on arrival; never stored raw.
- `schema_hash` (string): Short hash of the tool schema used.
- `service` (string, required): The MCP server's own name (serverInfo.name) or the API host, e.g. 'api.github.com'. Not your client's local alias.
- `version` (string): Version of the service/tool.

### `report_tool_success` (~176 tokens)

Report a successful tool call to the network

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.

Input parameters:

- `latency_ms` (integer): Observed call latency in milliseconds.
- `operation` (string, required): The tool or endpoint as the server names it, e.g. 'create_issue', not 'mcp__github__create_issue'.
- `reporter_id` (string): Optional stable agent id; hashed, never stored raw.
- `schema_hash` (string): Short hash of the tool schema used.
- `service` (string, required): The MCP server's own name (serverInfo.name) or the API host, e.g. 'api.github.com'. Not your client's local alias.
- `version` (string): Version of the service/tool.

### `report_recovery_outcome` (~141 tokens)

Report whether a recovery action worked

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.

Input parameters:

- `action` (string, required): What you tried, e.g. 'refresh_schema' ([a-z0-9_.-]).
- `fingerprint` (string, required): From check_tool_failure or report_tool_failure (32 hex chars).
- `reporter_id` (string): Optional stable agent id; hashed, never stored raw.
- `successful` (boolean, required): True when the action resolved the failure.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-failecho-failecho/failecho#diagnostics

## Score history

- 2026-09-22: 71
- 2026-09-21: 70
- 2026-09-20: 70
- 2026-09-19: 69
- 2026-09-18: 69
- 2026-09-17: 68
- 2026-09-16: 67
- 2026-09-15: 67
- 2026-09-14: 66
- 2026-09-13: 64
- 2026-09-12: 63
- 2026-09-11: 63
- 2026-09-10: 63

## Common questions

### What is the com.failecho/failecho MCP server?

com.failecho/failecho is an MCP server listed in the public MCP registry as com.failecho/failecho. Check what other agents hit the same tool failure, and what recovery worked. Ask before retrying. This page covers its hosted endpoint (https://failecho.com/mcp).

### Is the com.failecho/failecho MCP server safe to use?

com.failecho/failecho scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the com.failecho/failecho MCP server expose?

com.failecho/failecho exposes 4 tools: check_tool_failure, report_tool_failure, report_tool_success, report_recovery_outcome. Their descriptions and schemas cost roughly 978 tokens of context every time the server is loaded.

### Does the com.failecho/failecho MCP server require authentication?

No. We connected to com.failecho/failecho without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the com.failecho/failecho MCP server still maintained?

com.failecho/failecho is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://failecho.com/mcp
- Repository: https://github.com/FailEcho/failecho
- Website: https://failecho.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-failecho-failecho/failecho.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-failecho-failecho/failecho.json
- HTML version of this page: https://verifymcp.io/servers/com-failecho-failecho/failecho