io.github.guptaprakhariitr/verification-mcp

Citation Verification

Real-time fact-check, citation verification, and source-freshness for AI agents.

Endpointhttps://verification-mcp.atlasword.workers.dev/mcp (streamable-http)
Registry version0.1.1
Now3 tools · grade A (98) · pin ts_33f6a106f42af8ae5f4534dffc780a06 · protocol 2025-06-18
First / last listed2026-11-06 00:52 UTC / 2026-11-06 00:52 UTC
Grade over time2026-11-06: A (98), 3 tools

Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.

Timeline

First listing · 2026-11-06 00:52 UTC
3 tools, grade A (98)

Tools: fact_check cite_check source_freshness

Current tools (3)

fact_checkVerify a factual claim against authoritative sources (Wikipedia, Wikidata, Crossref academic citations). Returns a verdict ('supported' / 'contradicted' / 'mixed' / 'unverified'), a 0–1 confidence score, and the list of sources with excerpts. Use this when an agent is about to assert a fact it isn't 100% sure of, or when post-processing LLM output to flag possibly-hallucinated claims.
params: claim*
cite_checkVerify that one or more cited URLs (a) resolve, (b) match the cited claim text, and (c) aren't retracted. Useful when an LLM produced inline citations and you want to confirm they're real and on-point. Pass DOIs directly (e.g. '10.1038/nature12373') or full URLs. Up to 25 per call.
params: citations*
source_freshnessCheck whether a source URL is still live and how recently it was modified. Returns the HTTP last-modified header (if present), the most recent Wayback Machine snapshot, and a 'changed_recently' flag (last 90 days). Use this for RAG hygiene — flagging citations that point to pages that may have changed since the agent's training data.
params: url*

Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.