Server definition

Hash: sha256:932f8ed09ed643f49c9874aa458627367efc7506ae8d91423842fc7abbd7d7d9
What it is: What a remote MCP server returned when asked what it offers: 9 tools

The blob, as servednamed by its sha256

{
  "instructions": "Tomesphere MCP gives access to ~8.5M scientific papers (arXiv + biomedical: PMC / bioRxiv / medRxiv) with LLM-curated TLDRs, SPECTER2 embeddings, linked entities (genes/proteins/diseases), figures, and a citation graph. Use search_papers for topic queries, get_paper for a specific id, similar_papers / citations to walk the graph.",
  "tools": [
    {
      "description": "Get papers that cite the given paper (who refers to this work). Use when the user asks 'who cites X', 'what's the impact', or wants follow-up work. Note: 2024+ citation coverage is sparse; indexing in progress.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "arXiv ID or OpenAlex Work ID.",
            "type": "string"
          },
          "k": {
            "default": 25,
            "description": "Max citing papers (default 25, max 100).",
            "type": "integer"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "citations",
      "outputSchema": null
    },
    {
      "description": "Get the biomedical entities linked to a paper: genes, proteins, chemicals, diseases, species, mutations, cell lines, and clinical-trial (NCT) IDs. Accepts an arXiv ID, PMC ID, or bioRxiv/medRxiv DOI.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "arXiv ID, PMC ID, or 10.1101/… DOI.",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_entities",
      "outputSchema": null
    },
    {
      "description": "Get a paper's real figure images — URLs, labels, and captions. Most biomedical papers have figures; arXiv papers often don't. Accepts an arXiv ID, PMC ID, or bioRxiv/medRxiv DOI.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "arXiv ID, PMC ID, or 10.1101/… DOI.",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_figures",
      "outputSchema": null
    },
    {
      "description": "Fetch a paper's full body text as Markdown (methods, results, protocols, inline tables) — use for deep questions the abstract can't answer. Accepts an arXiv ID (2401.12345), a PMC ID (PMC5339222), or a bioRxiv/medRxiv DOI (10.1101/…).",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "arXiv ID, PMC ID, or 10.1101/… DOI.",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_full_text",
      "outputSchema": null
    },
    {
      "description": "Fetch a paper's full metadata: title, authors, year, abstract, TLDR (LLM-generated), key findings, citation count, GitHub repos, HuggingFace models/datasets, videos, peer reviews, and links. Accepts an arXiv ID (e.g. '2401.12345' or '1706.03762v5') or an OpenAlex Work ID (e.g. 'W4390723197'). Use when the user names a specific paper or pastes an arXiv link.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "arXiv ID like '2401.12345' or OpenAlex Work ID like 'W4390723197'.",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_paper",
      "outputSchema": null
    },
    {
      "description": "Resolve a gene/protein name (e.g. 'TP53', 'CD44') or UniProt accession to its 3D structure — returns the UniProt accession + AlphaFold model URL (and PDB when available). Great for a gene named in a paper's entities.",
      "inputSchema": {
        "properties": {
          "name": {
            "description": "Gene/protein symbol (TP53, CD44) or UniProt accession (P04637).",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "get_structure",
      "outputSchema": null
    },
    {
      "description": "Get the papers that this paper cites (its bibliography). Use when the user asks 'what does X cite' or 'show me the references'.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "arXiv ID or OpenAlex Work ID.",
            "type": "string"
          },
          "k": {
            "default": 25,
            "description": "Max references (default 25, max 100).",
            "type": "integer"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "references",
      "outputSchema": null
    },
    {
      "description": "Search 8.5 million academic papers (arXiv + biomedical: PMC / bioRxiv / medRxiv, all disciplines) by topic, keyword, author, or linked entity (gene / protein / disease). Each hit returns id, title, TLDR, type, and links. Use to find papers about a topic, e.g. 'transformer efficiency' or 'CRISPR base editing'.",
      "inputSchema": {
        "properties": {
          "k": {
            "default": 10,
            "description": "Number of results (default 10, max 25).",
            "type": "integer"
          },
          "query": {
            "description": "Natural-language search query. E.g. 'transformer attention efficiency', 'graph neural networks for molecular property prediction'.",
            "type": "string"
          },
          "year_max": {
            "description": "Latest publication year.",
            "type": "integer"
          },
          "year_min": {
            "description": "Earliest publication year, e.g. 2024.",
            "type": "integer"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_papers",
      "outputSchema": null
    },
    {
      "description": "Find papers semantically similar to a given paper using SPECTER2 embeddings (trained on scientific-citation triplets). Returns nearest neighbors with TLDR. Use when the user wants 'papers like X' or 'what's adjacent to this work'.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "arXiv ID or OpenAlex Work ID.",
            "type": "string"
          },
          "k": {
            "default": 10,
            "description": "Number of neighbors (default 10, max 25).",
            "type": "integer"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "similar_papers",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:932f8ed09ed643f49c9874aa458627367efc7506ae8d91423842fc7abbd7d7d9 | sha256sum