Corollary — scientific AI models, tools and databases

{
  "mcpServers": {
    "com.corollary-labs/corollary": {
      "url": "https://corollary-labs.com/mcp"
    }
  }
}

Indexed tools

Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.

6 shown · authentication unknown

• Compare the models or tools for a task

  compare_scientific_ai_for_task

  For a task such as 'protein structure prediction', 'protein design', 'antibody design', 'molecular docking', 'single-cell', 'ADMET', 'phage genomics' or 'CRISPR', return every model or tool Corollary lists for it — what each does, licence, whether it runs online — and guidance on how to choose between them.

  Schema valid · SHA-256 8fe2f12e49e5…

  View input schema

  {
    "type": "object",
    "properties": {
      "task": {
        "type": "string",
        "description": "The task, in plain words."
      }
    },
    "required": [
      "task"
    ],
    "additionalProperties": false
  }

• Explain one model, tool, database, pipeline or dataset

  get_scientific_ai_details

  Full reference for one entry: what it is, how it works, key facts, uses, strengths, limitations, citation, licence, and how to run it on Corollary. Pass a name ('RFdiffusion'), an id ('esmfold2', 'nf-core/rnaseq', 'facebook/esm2_t33_650M_UR50D') or a corollary-labs.com URL.

  Schema valid · SHA-256 ba4f61a3d4f2…

  View input schema

  {
    "type": "object",
    "properties": {
      "ref": {
        "type": "string",
        "description": "Name, id or Corollary page URL."
      }
    },
    "required": [
      "ref"
    ],
    "additionalProperties": false
  }

• How to do a scientific analysis on Corollary