Query and Analyze CIViC Cancer Genomics Data
CIViC MCP Server: Query cancer genomics and clinical variant interpretation data via GraphQL and SQL. Deploy to Cloudflare Workers.
Why it matters
Access and analyze complex cancer genomics and clinical variant interpretation data from the CIViC database. This asset enables structured querying via GraphQL and SQL, transforming raw API responses into usable datasets for research and analysis.
Outcomes
What it gets done
Execute GraphQL queries against the CIViC API.
Query pre-processed CIViC data using SQL.
Convert GraphQL responses into structured SQLite tables.
Manage and query intermediate datasets efficiently.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-civic | bash Capabilities
Tools your agent gets
Execute GraphQL queries against the CIViC API for cancer genomics data
Query pre-processed cancer variant data using SQL
Overview
CIViC MCP Server
What it does
CIViC MCP Server
Source README
MCP server for working with the CIViC (Clinical Interpretation of Variants in Cancer) database, enabling structured queries and analysis of cancer genomics and clinical variant interpretation information through GraphQL and SQL.
Installation
Deploy to Cloudflare Workers
git clone <repository-url>
cd civic-mcp-server
npm install
npm run deploy
Configuration
Claude Desktop
{
"mcpServers": {
"civic-mcp-server": {
"command": "npx",
"args": [
"mcp-remote",
"https://civic-mcp-server.quentincody.workers.dev/sse"
]
}
}
}
Available Tools
| Tool | Description |
|---|---|
civic_graphql_query |
Execute GraphQL queries against the CIViC API |
civic_query_sql |
Query pre-processed data using SQL |
Features
- GraphQL to SQL conversion: Automatically transforms CIViC API responses into structured SQLite tables
- Efficient data storage: Uses Cloudflare Durable Objects with SQLite for intermediate storage and queries
- Smart response handling: Optimizes performance by bypassing intermediate storage for small responses, errors, and schema queries
- Two-stage pipeline: GraphQL queries and SQL analysis of intermediate data
- Dataset management: Helper endpoints for managing intermediate datasets
- Three MCP prompts: get-variant-evidence, get-variant-assertions, get-variant-data with reliable GraphQL generation
Usage Examples
What are the latest BRAF mutation data?
Show all therapeutic interpretations for lung cancer variants
Find genes with the most data in the CIViC database
/get-variant-evidence molecularProfileName:"TP53 Mutation" diseaseName:"Lung Adenocarcinoma" evidenceType:"PROGNOSTIC" first:"200"
/get-variant-assertions molecularProfileName:"TPM3-NTRK1 Fusion" therapyName:"Larotrectinib" status:"ALL"
Notes
Implements MCP specification 2025-06-18. Requires deployment to Cloudflare Workers and provides dataset management endpoints at /datasets. Uses intelligent response handling to optimize context usage, storing large results in SQLite and returning small responses directly.
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.