
CiteStamp MCP server
Which servers in the official MCP registry are CiteStamp's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-21
- Registry namecom.citestamp/citestampverified in the MCP registry
The registry name sits under citestamp.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools7
- Server calls itselfcitestamp
- Server version1.3.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 390 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 4 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer567 ms
- Space in an agent's context≈ 1,787 tokensthe definitions of all its tools (7), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Check a reference list against open registries
- not sure · Walk a paper's citation graph with typed edges
- cannot · Sign claims about your own papers with ORCID
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
what_supportsEdges recorded as SUPPORTING the given work or claim: human-signed support claims plus successful replication outcomes coded by the FORRT Replication Database. Use when a user asks whether a finding held up or was replicated.
what_refutesEdges recorded as REFUTING the given work or claim: human-signed refutations plus failed replication outcomes coded by the FORRT Replication Database. Use when a user asks whether a finding failed to replicate or has been contradicted.
what_citesWorks that CITE the given DOI (incoming citations). Use when a user asks who cites a paper, how much a work has been cited, or whether a claimed 'cited by' is real. Returns edges with tier + attribution; paged.
references_ofWhat the given work CITES (its reference list). Use when a user asks what a paper relies on, whether a specific citation in it exists, or wants to check a reference before reusing it. Paged.
edges_aboutEvery edge touching the given work in either direction, each tagged asserted|inferred with attribution and provenance. Use when a user asks 'what is known about this paper's citations' or wants the whole neighbourhood in one call. Paged.
retraction_listingWhether the Retraction Watch database lists the given DOI as retracted, from the dated export CiteStamp joins weekly. Use when a user asks whether a paper has been retracted or carries a retraction notice. Not listed means not in that…
check_referenceWhether a reference resolves to a real work. Use when an answer is about to cite a paper. Give a DOI, an arXiv id or the reference as written. Answers found, confirm (with the reason), not found in the named sources on a date, or couldn't…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"citestamp": {
"type": "http",
"url": "https://mcp.citestamp.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http citestamp https://mcp.citestamp.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.citestamp.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.