Language models invent citations. CiteStamp is a live, typed citation graph your agent can query before it emits a reference — with human-signed claims and machine-inferred coverage kept strictly apart, so your agent always knows which kind of evidence it is holding.
The graph speaks Model Context Protocol over Streamable HTTP. Point your agent at:
https://mcp.citestamp.com/mcp
Five tools, each taking an identifier (DOI in any common form) and an optional asserted_only flag:
| tool | answers |
|---|---|
| edges_about | every claim where the paper appears, either side |
| what_supports | claims that something supports this paper |
| what_refutes | claims that something refutes this paper |
| what_cites | papers whose reference lists include this one |
| references_of | what this paper itself cites |
Every result carries a tier (asserted = human-signed, inferred = machine-derived), an attribution, and provenance. Set asserted_only=true when only name-on-the-record claims should count.
curl -s https://api.citestamp.com/api/v1/ask/edges_about -H "Content-Type: application/json" -d JSON_BODY
where JSON_BODY is: {"id": "10.5281/zenodo.18182662"}
Anonymous asking is open at 10 requests a minute per IP. A free key raises limits; metered tiers exist for production agent traffic: info@citestamp.com.
Machine-readable description at /.well-known/citestamp.json; a plain-text brief for LLM crawlers at /llms.txt and /llms-full.txt.