Server definition

Hash: sha256:de99f627c666f92cece2a01acee0d58cbb72eb6e5ac9e2b21b01a65d5c8a4e5a
What it is: What a remote MCP server returned when asked what it offers: 6 tools

The blob, as servednamed by its sha256

{
  "instructions": "Call these when a question turns on a specific paper's citations, references, support, refutation or replication record, or when a reference is about to be cited and should be grounded first; identify the work by DOI, arXiv id or OpenAlex id. CiteStamp grounds citations against a typed, identity-resolved graph that hard-separates asserted (human-signed) from inferred (machine-derived) edges. Every result carries a tier, an attribution, and provenance. Most inferred edges are attributed openalex-snapshot: bulk citation metadata projected from OpenAlex, which publishes it at source. The rest are openalex-extracted reference lists and zenodo-depositor-declared relations from CiteStamp's own sweeps; a small typed tier of supports/refutes edges is attributed forrt-fred - replication outcomes (successful/failed) coded by the FORRT Replication Database, CC BY 4.0 per edge, not signed claims. Inferred edges are not independent of the metadata they were derived from, and a sparse answer means the sweeps have not reached a work yet rather than that nothing cites it. Prefer asserted_only=true when you want only human-signed claims; leave it false for the broader recall. ANSWERS ARE PAGED: a well-cited work has thousands of edges and every result carries a page object with has_more and, where it is exact, inferred_total. Do not read one page as the complete answer - raise limit (max 1000) or page with offset while has_more is true, advancing by the limit you asked for rather than by the number of rows returned. Separate from the graph, retraction_listing reports whether the Retraction Watch database lists a DOI as retracted, from a dated export with its own attribution and licence; it does not check the publisher record.",
  "tools": [
    {
      "description": "Every 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.",
      "inputSchema": {
        "properties": {
          "asserted_only": {
            "default": false,
            "description": "If true, restrict to human-signed (asserted) edges. If false (default), return both asserted and machine-inferred edges.",
            "type": "boolean"
          },
          "identifier": {
            "description": "DOI, arXiv id, OpenAlex id, or internal claim id",
            "type": "string"
          },
          "limit": {
            "default": 100,
            "description": "Maximum edges to return per tier (default 100, max 1000). Well-cited works have thousands; the response reports has_more and inferred_total so you can tell a page from the whole answer.",
            "maximum": 1000,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "How many edges to skip, for paging. Advance by the LIMIT you asked for, not by the number of results you got back — duplicates are removed after the window is taken, so a page can return fewer rows than it consumed. Keep going while has_more is true.",
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "identifier"
        ],
        "type": "object"
      },
      "name": "edges_about",
      "outputSchema": null
    },
    {
      "description": "What 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.",
      "inputSchema": {
        "properties": {
          "asserted_only": {
            "default": false,
            "description": "If true, restrict to human-signed (asserted) edges. If false (default), return both asserted and machine-inferred edges.",
            "type": "boolean"
          },
          "identifier": {
            "description": "DOI, arXiv id, OpenAlex id, or internal claim id",
            "type": "string"
          },
          "limit": {
            "default": 100,
            "description": "Maximum edges to return per tier (default 100, max 1000). Well-cited works have thousands; the response reports has_more and inferred_total so you can tell a page from the whole answer.",
            "maximum": 1000,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "How many edges to skip, for paging. Advance by the LIMIT you asked for, not by the number of results you got back — duplicates are removed after the window is taken, so a page can return fewer rows than it consumed. Keep going while has_more is true.",
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "identifier"
        ],
        "type": "object"
      },
      "name": "references_of",
      "outputSchema": null
    },
    {
      "description": "Whether 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 export; the publisher record is not checked.",
      "inputSchema": {
        "properties": {
          "identifier": {
            "description": "DOI in any common form (10.x/y, doi:10.x/y or a doi.org URL)",
            "type": "string"
          }
        },
        "required": [
          "identifier"
        ],
        "type": "object"
      },
      "name": "retraction_listing",
      "outputSchema": null
    },
    {
      "description": "Works 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.",
      "inputSchema": {
        "properties": {
          "asserted_only": {
            "default": false,
            "description": "If true, restrict to human-signed (asserted) edges. If false (default), return both asserted and machine-inferred edges.",
            "type": "boolean"
          },
          "identifier": {
            "description": "DOI, arXiv id, OpenAlex id, or internal claim id",
            "type": "string"
          },
          "limit": {
            "default": 100,
            "description": "Maximum edges to return per tier (default 100, max 1000). Well-cited works have thousands; the response reports has_more and inferred_total so you can tell a page from the whole answer.",
            "maximum": 1000,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "How many edges to skip, for paging. Advance by the LIMIT you asked for, not by the number of results you got back — duplicates are removed after the window is taken, so a page can return fewer rows than it consumed. Keep going while has_more is true.",
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "identifier"
        ],
        "type": "object"
      },
      "name": "what_cites",
      "outputSchema": null
    },
    {
      "description": "Edges 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.",
      "inputSchema": {
        "properties": {
          "asserted_only": {
            "default": false,
            "description": "If true, restrict to human-signed (asserted) edges. If false (default), return both asserted and machine-inferred edges.",
            "type": "boolean"
          },
          "identifier": {
            "description": "DOI, arXiv id, OpenAlex id, or internal claim id",
            "type": "string"
          },
          "limit": {
            "default": 100,
            "description": "Maximum edges to return per tier (default 100, max 1000). Well-cited works have thousands; the response reports has_more and inferred_total so you can tell a page from the whole answer.",
            "maximum": 1000,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "How many edges to skip, for paging. Advance by the LIMIT you asked for, not by the number of results you got back — duplicates are removed after the window is taken, so a page can return fewer rows than it consumed. Keep going while has_more is true.",
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "identifier"
        ],
        "type": "object"
      },
      "name": "what_refutes",
      "outputSchema": null
    },
    {
      "description": "Edges 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.",
      "inputSchema": {
        "properties": {
          "asserted_only": {
            "default": false,
            "description": "If true, restrict to human-signed (asserted) edges. If false (default), return both asserted and machine-inferred edges.",
            "type": "boolean"
          },
          "identifier": {
            "description": "DOI, arXiv id, OpenAlex id, or internal claim id",
            "type": "string"
          },
          "limit": {
            "default": 100,
            "description": "Maximum edges to return per tier (default 100, max 1000). Well-cited works have thousands; the response reports has_more and inferred_total so you can tell a page from the whole answer.",
            "maximum": 1000,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "How many edges to skip, for paging. Advance by the LIMIT you asked for, not by the number of results you got back — duplicates are removed after the window is taken, so a page can return fewer rows than it consumed. Keep going while has_more is true.",
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "identifier"
        ],
        "type": "object"
      },
      "name": "what_supports",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:de99f627c666f92cece2a01acee0d58cbb72eb6e5ac9e2b21b01a65d5c8a4e5a | sha256sum