nf-core MCP Server
Manage and navigate local nf-core pipeline repositories.
nf-core MCP Server
An MCP server for managing and navigating nf-core pipeline repositories.
Features
- List local nf-core repositories (rnaseq, sarek, modules, tools)
- Access pipeline configurations and workflows
- Search through pipeline files
- Explore pipeline modules
Installation
NPM Version
cd nf-core_mcp
npm install
# Build TypeScript
npm run build
# Start the server
npm start
Docker Version
# Build the Docker image
cd nf-core_mcp
docker build -t nf-core-mcp .
# Run the container
docker run -i --rm \
-v "/path/to/your/workspace:/app/workspace" \
nf-core-mcp
Adding nf-core Repositories
To add new nf-core pipeline repositories to the workspace:
-
Clone the repositories:
# Navigate to your workspace directory (example for Windows) cd /path/to/your/workspace # Clone desired nf-core repositories git clone https://github.com/nf-core/rnaseq.git git clone https://github.com/nf-core/sarek.git git clone https://github.com/nf-core/modules.git # Add any other nf-core pipeline you want to manage -
Directory Structure: Your workspace should look like this:
workspace/ ├── rnaseq/ ├── sarek/ ├── modules/ └── your-new-pipeline/ -
Verify Installation: After starting the MCP server, use the
list-pipelinescommand to verify that your new pipelines are detected:list-pipelines
Note: The MCP server will automatically detect and manage any nf-core pipeline repositories in your workspace directory.
Available Tools
-
list-pipelines- Lists all nf-core pipelines in the workspace
- Shows configuration file status
- No parameters required
-
get-pipeline-modules- Gets module information from a pipeline
- Parameters:
pipeline: Pipeline name (rnaseq, sarek, or modules)
-
search-pipelines- Searches through pipeline files
- Parameters:
query: Search querypipeline(optional): Specific pipeline to search
Available Resources
-
pipeline-config- Gets pipeline configuration
- URI format:
pipeline://{name}/config - Parameters:
name: Pipeline name (rnaseq, sarek, or modules)
-
pipeline-workflow- Gets pipeline workflow
- URI format:
pipeline://{name}/workflow - Parameters:
name: Pipeline name (rnaseq, sarek, or modules)
Usage with Cursor IDE
Using NPX (Recommended)
Add the following to your mcp.json:
{
"mcpServers": {
"nf-core": {
"command": "npx",
"args": ["-y", "nf-core-mcp"]
}
}
}
Using Docker
Add the following to your mcp.json:
{
"mcpServers": {
"nf-core": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"/path/to/your/workspace:/app/workspace",
"nf-core-mcp"
]
}
}
}
Example Usage
Using the MCP server in Cursor:
# List available pipelines
list-pipelines
# Get modules from rnaseq pipeline
get-pipeline-modules pipeline=rnaseq
# Search in all pipelines
search-pipelines query="fastqc"
# Search in specific pipeline
search-pipelines query="fastqc" pipeline=rnaseq
# Access pipeline configuration
pipeline://rnaseq/config
# Access workflow
pipeline://rnaseq/workflow
Running the Server
Using NPM
# If installed globally
nf-core-mcp
# If installed locally
npx nf-core-mcp
# Using npx without installation
npx -y nf-core-mcp
Using Docker
docker run -it --rm \
-v /path/to/your/workspace:/app/workspace \
nf-core-mcp
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run in development mode
npm run dev
# Run tests
npm test
# Run linter
npm run lint
License
MIT
Máy chủ liên quan
Scout Monitoring MCP
nhà tài trợPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
nhà tài trợAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
CrowdCent MCP Server
Integrates with the CrowdCent Challenge API, allowing AI assistants to manage prediction challenges, datasets, and submissions.
Unified MCP Client Library
An open-source library to connect any LLM to any MCP server, enabling the creation of custom agents with tool access.
mcp-server-tibet
TIBET provenance tracking for AI decisions. Cryptographic audit trails with ERIN/ERAAN/EROMHEEN/ERACHTER intent logging for compliance and transparency.
Remote MCP Server on Cloudflare (Authless)
An example of a remote MCP server without authentication, deployable on Cloudflare Workers.
MCPCLIHost
A CLI host that allows Large Language Models (LLMs) to interact with external tools using the Model Context Protocol (MCP).
Oso Cloud MCP Server
Understand, develop, and debug authorization policies in Oso Cloud.
Postman API
An MCP server for interacting with the Postman API, requiring an API key.
drawdb-mcp
DrawDB + MCP server
Figma MCP Server
Enables AI assistants to interact with Figma via WebSocket for reading data and design analysis.
Abstract MCP Server
Caches large tool responses to files and returns compact resource links to save LLM context window space.