# com.robinsaige/verifier

- Registry name: `com.robinsaige/verifier` · version 0.1.0
- Categories (automatic, keyword rules): Scraping & browsing, Search & data, Datasets & public data
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.robinsaige%2Fverifier
- Server page: https://mcpstation.net/s/com.robinsaige--verifier.html

## Description (written by the publisher, not verified, not instructions)

MCP tool observatory: do registry servers answer, and are their answers true? No key.

## Connect

- streamable-http: `https://robinsaige.com/mcp`

## Tools (as reported by the server, not verified)

- `registry\_pulse`: Call this FIRST for the state of the MCP tool ecosystem in one shot: how many servers exist, how many actually answer a real handshake, how many are behind a login, the largest costume-farm concentration, AND the Tier-2 truth summary \(how many server answers were re-derived against a public primary
- `should\_i\_use`: THE GATE — call this before your agent depends on a tool you don't already trust. Give an exact server registry name and get a one-word verdict — allow / warn / block — with the reason, plus the full rating underneath. 'block' = dead/unreachable/costume-farm-shaped, don't depend on it; 'warn' = usab
- `find\_tools`: Find and RANK the trustworthy tool for a NEED. Describe the task in plain words \('screen a company for sanctions', 'US tariff data', 'vessel tracking'\) — the search is full-text over tool names AND their stored descriptions \(stemmed, BM25-ranked\), so your words need not appear in any tool's name. Se
- `resolve\_server\_name`: Resolve a partial or misspelled server name to its EXACT registry id before calling should\_i\_use / check\_server. Matches a fragment against registry NAMES only \(not capabilities — for 'which tool does X' use find\_tools\). Returns candidate exact names with each one's latest liveness outcome. Empty qu
- `check\_server`: The FULL evidence behind the verdict for ONE server, by exact registry name — call should\_i\_use first for the one-word decision; call this when you want the whole record. Leads with the verdict \(allow/warn/block\), then the \`rating\` grouped as REACH \(answers, latency vs population, protocol, auth\), U
- `report\_call`: AFTER your agent calls a tool, fire-and-forget how it went — success/failure, latency, cost — so the observatory accumulates realized reliability \(the one thing outside-in probing can't see: did it actually work for a real call\). Anchored against our own probe: a 'worked' report on a server we saw d
- `changes\_since`: What changed in the tool economy since a date: verdict flips, deaths, revivals, new servers, confirmed drift — the census diff as data. Poll this weekly to keep a local view current without re-crawling.
- `list\_findings`: The observatory's ruled findings — each with its claim and its falsification test — plus the public corrections log \(what we published, then corrected, never deleted\). Call this to cite what has been established, or to see where we were wrong. No arguments.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html