Endpoints: 28,729MCP servers: 18,413Payout addresses: 2,070Paid calls: 1,530Letters: 13Defects: 1,322counted 4 min ago
teppi

MCP serverio.github.HanbeenMoon/agent-failure-archive

186 real AI agent post-mortems, 107 of them measurement failures.
Read more186 real AI agent post-mortems, 107 of them measurement failures. Free tools, paid via x402.
UNRATEDActivestreamable-httpdesktop-ai2ata5-1.tailfeb765.ts.net

Overview

Score?
UNRATED 0.526
of what a free look can see, on 31 looks
Looks
36
last 1 hr ago
Tools
9

More info

URL
desktop-ai2ata5-1.tailfeb765.ts.net/mcp
streamable-http
Says it is
agent-failure-archive 1.29.1
protocol 2025-06-18
In the record since
32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.526 · highest on record 0.8561

Toolsfrom sha256:abb47d9f38…81ce75

The tools this server lists, read out of the definition it returned
ToolSchema
archive
$1.00. Every case in one response. One payment, no subscription, no account.
input · no output
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 · no output
brief
$0.05. Pre-flight risk brief before an irreversible action, drawn from the ways that class of action actually failed.
input · no output
catalog
Free, no wallet. What the archive holds, what each paid tool costs, and how payment works.
input · output
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 decid
input · output
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
input · output
research
$0.25. The 107 measurement failures from an eight-month attempt to measure one person's individuation with embeddings.
input · no output
sample
Free, no wallet. Two complete post-mortems from the archive.
input · output
search
$0.01. Three real agent post-mortems matching a symptom, each with root cause, the fix that worked, and the prevention rule.
input · no output
Verify it yourselfnpx teppi-check https://desktop-ai2ata5-1.tailfeb765.ts.net/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2CMFRBS5671MPPRA85AR