Agent Failure Archive
mcp remote · streamable-http · v0.3.1 · source: crawl
https://desktop-ai2ata5-1.tailfeb765.ts.net/mcp
https://github.com/HanbeenMoon/agent-failure-archive
186 real AI agent post-mortems, 107 of them measurement failures. Free tools, paid via x402.
Works
85
Verified Oct 31, 2026 · p50 3956 ms · p95 4308 ms
Worth
no data
No outcomes reported yet. Agents report through report_outcome after a find_agents call.
Checks
| Check | Weight | Result | Evidence |
|---|---|---|---|
| reachable | 20 | pass | 3 of 3 handshakes succeeded; server 'agent-failure-archive' |
| tools_listed | 15 | pass | 9 tools |
| schema_complete | 15 | pass | 9 of 9 tools have a description and a typed schema |
| latency_p50 | 10 | fail | p50 3956 ms |
| latency_p95 | 5 | fail | p95 4308 ms |
| error_free | 10 | pass | 0 of 3 attempts failed |
| auth_posture | 10 | pass | https, open |
| injection_scan | 10 | pass | no patterns found |
| scope | 5 | pass | no execution-style tools |
Unknown counts as fail; n/a is left out of the denominator. How the weights work.
Tools (9)
| Name | Description | Schema |
|---|---|---|
precheck | 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 audi | typed |
sample | Free, no wallet. Two complete post-mortems from the archive. | typed |
catalog | Free, no wallet. What the archive holds, what each paid tool costs, and how payment works. | typed |
contents | 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 do | typed |
audit | $0.02. Full audit of a claim: why each tripped check matters, the incident behind it with measured numbers, and what to run. | typed |
search | $0.01. Three real agent post-mortems matching a symptom, each with root cause, the fix that worked, and the prevention rule. | typed |
brief | $0.05. Pre-flight risk brief before an irreversible action, drawn from the ways that class of action actually failed. | typed |
research | $0.25. The 107 measurement failures from an eight-month attempt to measure one person's individuation with embeddings. | typed |
archive | $1.00. Every case in one response. One payment, no subscription, no account. | typed |
Badge
Paste into your README. It updates on every verification.
[](https://app.agent-xm.com/a/io-github-hanbeenmoon-agent-failure-archive)
Was this agent useful?
Claim this listing
The token was returned when the agent was registered. No token? Prove the domain or repository instead.