MCP Server

Agent Failure Archive

io.github.HanbeenMoon/agent-failure-archive
AI & Agents Search & Research Public & reachable MCP 2025-11-25

What this MCP does

Provides searchable post-mortems, audits, prechecks, and risk briefs about AI agent failures and measurement mistakes.

archive
$1.00. Every case in one response. One payment, no subscription, no account.
Input schema
{'type': 'object', 'title': 'archiveArguments', 'properties': {}}
audit
$0.02. Full audit of a claim: why each tripped check matters, the incident behind it with measured numbers, and what to run.
Input schema
{'type': 'object', 'title': 'auditArguments', 'required': ['claim'], 'properties': {'claim': {'type': 'string', 'title': 'Claim'}, 'evidence': {'type': 'string', 'title': 'Evidence', 'default': ''}}}
brief
$0.05. Pre-flight risk brief before an irreversible action, drawn from the ways that class of action actually failed.
Input schema
{'type': 'object', 'title': 'briefArguments', 'required': ['action'], 'properties': {'action': {'type': 'string', 'title': 'Action'}}}
catalog
Free, no wallet. What the archive holds, what each paid tool costs, and how payment works.
Input schema
{'type': 'object', 'title': 'catalogArguments', 'properties': {}}
Output schema
{'type': 'object', 'title': 'catalogOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
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 dollar.
Input schema
{'type': 'object', 'title': 'contentsArguments', 'properties': {'theme': {'type': 'string', 'title': 'Theme', 'default': ''}}}
Output schema
{'type': 'object', 'title': 'contentsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
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 audit tool adds why each matters, the real incident with the numbers measured at the time, and what to run.
Input schema
{'type': 'object', 'title': 'precheckArguments', 'required': ['claim'], 'properties': {'claim': {'type': 'string', 'title': 'Claim'}, 'evidence': {'type': 'string', 'title': 'Evidence', 'default': ''}}}
Output schema
{'type': 'object', 'title': 'precheckOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
research
$0.25. The 107 measurement failures from an eight-month attempt to measure one person's individuation with embeddings.
Input schema
{'type': 'object', 'title': 'researchArguments', 'properties': {'q': {'type': 'string', 'title': 'Q', 'default': ''}}}
sample
Free, no wallet. Two complete post-mortems from the archive.
Input schema
{'type': 'object', 'title': 'sampleArguments', 'properties': {}}
Output schema
{'type': 'object', 'title': 'sampleOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
search
$0.01. Three real agent post-mortems matching a symptom, each with root cause, the fix that worked, and the prevention rule.
Input schema
{'type': 'object', 'title': 'searchArguments', 'required': ['q'], 'properties': {'q': {'type': 'string', 'title': 'Q'}}}
Added
archive
Sept. 17, 2026, 12:42 p.m.
Added
research
Sept. 17, 2026, 12:42 p.m.
Added
brief
Sept. 17, 2026, 12:42 p.m.
Added
search
Sept. 17, 2026, 12:42 p.m.
Added
audit
Sept. 17, 2026, 12:42 p.m.
Added
contents
Sept. 17, 2026, 12:42 p.m.
Added
catalog
Sept. 17, 2026, 12:42 p.m.
Added
sample
Sept. 17, 2026, 12:42 p.m.
Added
precheck
Sept. 17, 2026, 12:42 p.m.