# Corollary Labs Corollary MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.corollary-labs%2Fcorollary
Registry id: `mcp-registry/com.corollary-labs/corollary`
Status: live (checked 2026-11-22T12:28:31.194Z)

## Verdict

Corollary Labs Corollary MCP server answered 99.99% of Glimind's liveness checks over 30 days, better than 41% of MCP servers, with 829 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (92/100) across 6 tools, costing an agent about 875 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.99% | 41% of MCP servers |
| Median handshake latency | 829 ms | 8% of MCP servers |
| p95 handshake latency | 1126 ms | — |
| Checks in 30 days | 6,935 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 2 min | — |
| Agent-readiness score | 92/100 (A) | 65% of MCP servers |
| Tools | 6 | — |
| Tool-list size for an agent | ~875 tokens | 72% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "corollary-labs-corollary-mcp-server": {
      "type": "http",
      "url": "https://corollary-labs.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http corollary-labs-corollary-mcp-server https://corollary-labs.com/mcp
```

## Tools (6)

- `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
- `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 
- `how_to_run_science_task`: For a piece of scientific work someone wants done — 'annotate a phage genome', 'deconvolve bulk RNA-seq into cell types', 'check assembly completeness', 'dock a
- `list_science_tasks`: Every scientific analysis Corollary has a page and a method for, with its URL.
- `list_scientific_ai_tasks`: The task categories Corollary compares models and tools in, with a page URL for each.
- `search_scientific_ai`: Search Corollary's catalogue of open scientific AI models (protein structure prediction, protein design, docking, antibodies, genomics, single-cell, chemistry/A

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
