# Agent Failure Archive (remote · desktop-ai2ata5-1.tailfeb765.ts.net)

186 real AI agent post-mortems, 107 of them measurement failures. Free tools, paid via x402.

- Trust score: 0/100 (low)
- Change this week: −67
- Registry status: active
- Liveness: dead
- Owner verified: no
- Last scored: 2026-09-14

> **Dead**: every channel of this server has been unreachable for long enough to be marked dead. Its trust score is pinned to 0 and does not recover automatically.

## Components

- remote · `desktop-ai2ata5-1.tailfeb765.ts.net`: 0/100 (this document), [markdown](https://verifymcp.io/servers/hanbeenmoon-agent-failure-archive/desktop-ai2ata5-1.md), [page](https://verifymcp.io/servers/hanbeenmoon-agent-failure-archive/desktop-ai2ata5-1)

## Channel facts

- Endpoint: `https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.1`

## 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 2026-09-14.

- **Endpoint Security**: 11/100
  - TLS not yet verified: we couldn't open a connection to check the certificate.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS not yet verified: we couldn't read the response headers to check for it.
  - DNSSEC not yet verified: we couldn't validate it against a resolver.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but we couldn't connect to verify it.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Agent Failure Archive MCP server?

Agent Failure Archive is a hosted endpoint at https://desktop-ai2ata5-1.tailfeb765.ts.net/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 hanbeenmoon-agent-failure-archive 'https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "hanbeenmoon-agent-failure-archive": {
      "url": "https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "hanbeenmoon-agent-failure-archive": {
      "type": "http",
      "url": "https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.hanbeenmoon-agent-failure-archive]
url = "https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hanbeenmoon-agent-failure-archive": {
      "type": "remote",
      "url": "https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add hanbeenmoon-agent-failure-archive --url 'https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  hanbeenmoon-agent-failure-archive:
    url: "https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "hanbeenmoon-agent-failure-archive": {
      "Transport": "http",
      "Url": "https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add hanbeenmoon-agent-failure-archive -t streamable-http -u 'https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp'
```

### Other

```json
{
  "mcpServers": {
    "hanbeenmoon-agent-failure-archive": {
      "type": "http",
      "url": "https://desktop-ai2ata5-1.tailfeb765.ts.net/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.

### 2026-09-14 (score 0, −13)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-13 (score 13, −14)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-12 (score 27, −13)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-11 (score 40, −14)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-10 (score 54, −13)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-09 (score 67, 0)

- [security regression] DNSSEC: fail → unverified

### 2026-09-08 (score 67, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: fail → unverified
- [security regression] Stability: 0.43 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-09-07 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `precheck` (~86 tokens)

Free, no wallet. Check a conclusion against nine known ways of fooling yourself and get back which checks it trips plus the question each one asks. Use it before writing 'we found that'. The paid audit tool adds why each matters, the real incident with the numbers measured at the time, and what to run.

Input parameters:

- `claim` (string, required)
- `evidence` (string)

Output parameters:

- `result` (string)

### `sample` (~22 tokens)

Free, no wallet. Two complete post-mortems from the archive.

Output parameters:

- `result` (string)

### `catalog` (~28 tokens)

Free, no wallet. What the archive holds, what each paid tool costs, and how payment works.

Output parameters:

- `result` (string)

### `contents` (~57 tokens)

Free, no wallet. Every case title in the archive, tagged with the trap it illustrates. Titles only, no bodies. Read this to see what the paid archive actually contains before deciding it is worth a dollar.

Input parameters:

- `theme` (string)

Output parameters:

- `result` (string)

### `audit` (~52 tokens)

$0.02. Full audit of a claim: why each tripped check matters, the incident behind it with measured numbers, and what to run.

Input parameters:

- `claim` (string, required)
- `evidence` (string)

### `search` (~45 tokens)

$0.01. Three real agent post-mortems matching a symptom, each with root cause, the fix that worked, and the prevention rule.

Input parameters:

- `q` (string, required)

### `brief` (~39 tokens)

$0.05. Pre-flight risk brief before an irreversible action, drawn from the ways that class of action actually failed.

Input parameters:

- `action` (string, required)

### `research` (~38 tokens)

$0.25. The 107 measurement failures from an eight-month attempt to measure one person's individuation with embeddings.

Input parameters:

- `q` (string)

### `archive` (~27 tokens)

$1.00. Every case in one response. One payment, no subscription, no account.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/hanbeenmoon-agent-failure-archive/desktop-ai2ata5-1#diagnostics

## Score history

- 2026-09-14: 0
- 2026-09-13: 13
- 2026-09-12: 27
- 2026-09-11: 40
- 2026-09-10: 54
- 2026-09-09: 67
- 2026-09-08: 67
- 2026-09-07: 67
- 2026-09-06: 66
- 2026-09-05: 66
- 2026-09-04: 65
- 2026-09-03: 65
- 2026-09-02: 64
- 2026-09-01: 64
- 2026-08-31: 63
- 2026-08-30: 63
- 2026-08-29: 62
- 2026-08-28: 62
- 2026-08-27: 62
- 2026-08-26: 61
- 2026-08-25: 58

## Common questions

### What is the Agent Failure Archive MCP server?

Agent Failure Archive is an MCP server listed in the public MCP registry as io.github.HanbeenMoon/agent-failure-archive. 186 real AI agent post-mortems, 107 of them measurement failures. Free tools, paid via x402. This page covers its hosted endpoint (https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp).

### Is the Agent Failure Archive MCP server safe to use?

Agent Failure Archive scores 0 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 Agent Failure Archive MCP server expose?

Agent Failure Archive exposes 9 tools: precheck, sample, catalog, contents, audit, and 4 more. Their descriptions and schemas cost roughly 394 tokens of context every time the server is loaded.

### Does the Agent Failure Archive MCP server require authentication?

Its publisher declares no required credentials for Agent Failure Archive. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Agent Failure Archive MCP server still maintained?

Agent Failure Archive has been unreachable for long enough that we treat it as dead, and its score is pinned to zero. We last reached this channel on 7 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://desktop-ai2ata5-1.tailfeb765.ts.net/mcp
- Repository: https://github.com/HanbeenMoon/agent-failure-archive
- Changelog RSS feed: https://verifymcp.io/servers/hanbeenmoon-agent-failure-archive/desktop-ai2ata5-1.xml
- Changelog JSON feed: https://verifymcp.io/servers/hanbeenmoon-agent-failure-archive/desktop-ai2ata5-1.json
- HTML version of this page: https://verifymcp.io/servers/hanbeenmoon-agent-failure-archive/desktop-ai2ata5-1