OpenCRAVAT
About
Genetic variant annotation Browse OpenCRAVAT MCP Server for Claude, Cursor, VS Code, and other AI agents.
Details
- Author
- karchinlab
- Categories
- Other
Jump to
Setup
Install OpenCRAVAT in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/karchinlab/oc-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
It exposes MCP tools that let an MCP client:
- Discover which OpenCRAVAT annotators are being run (a curated default set).
- Inspect annotator output schemas (field names/types/descriptions).
- Annotate variants by:
- genomic coordinates (chrom/pos/ref/alt). Accepts only GRCh38/hg38 coordinates.
- dbSNP rsID
- ClinGen Allele Registry ID (CAid)
- HGVS (g./c./p.)
To connect to Claude, followthese instructions. Use the URL above, and do not set up auth. No user-specific data is needed for the MCP to work. Remember to enable the MCP for your chat.
To connect with ChatGPT, you must enable developer mode, then add a custom app:
- Open Settings
- Go to Apps
- In Advanced Settings, use the toggle to turn on “Developer Mode”
- Click Create App
- Use the URL above as the “MCP Server URL”
- Set Authentication to “No Auth”
- Add a name to the MCP App that you’ll easily recognize, such as “OpenCRAVAT”
You will have to add the MCP to a new chat using the + icon in the lower left of the chat box.
- Node.js (recent enough for modern TypeScript tooling; Node 18+ recommended)
- npm
To connect to your MCP server from Claude Desktop, followAnthropic's Quickstartand within Claude Desktop go to Settings > Developer > Edit Config.
{ "mcpServers": { "OpenCRAVAT": { "command": "npx", "args": [ "mcp-remote", "http://localhost:8787/mcp" ] } } }
Restart Claude and you should see the tools become available.
Bioinformatics data for AI agents — gene search, protein structures, clinical variants, PubMed literature, and DNA sequences via NCBI and UniProt. No API key required.
Interact with Omics AI Explorer networks for genomics research and data analysis.
Interact with DROMA drug-omics association analysis databases using natural language.
A search server for PubMed, the biomedical literature database, using a pure Node.js implementation.
Unofficial server for accessing Open Targets platform data for gene-drug-disease associations research.
Control anaerobic digestion modeling (ADM1) using natural language.
MCP server for generating, scoring and embedding genomic sequences using Evo 2
Unified access to global medical terminologies: ICD-11, SNOMED CT, LOINC, RxNorm, MeSH. 27 tools for medical coding, terminology lookup, and crosswalk mappings.
30+ pharma medical writing prompts as callable MCP tools — manuscripts, abstracts, publication plans and more. Built by a CMPP-certified PhD neuroscientist.
Medical terminology intelligence for AI agents — ICD-10-CM lookup, MedDRA hierarchy and SOC mapping, RxNorm drug concepts, CTCAE v5.0 grading, and cross-terminology mapping.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



