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-pipelines
command 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
Related Servers
MCP Servers Nix
A Nix-based configuration framework for deploying MCP servers with ready-to-use packages, supporting modular and reproducible builds.
MCP Code Crosscheck
A server for bias-resistant AI code review using cross-model evaluation.
EdgeOne Pages MCP
An MCP server and client implementation for EdgeOne Pages Functions, supporting OpenAI-formatted requests.
AntBot MCP Server
A TypeScript MCP server for integrating with the AntBot AI-based RPA platform, handling tool listing and execution.
Hyperlend
Enables AI agents to interact with the Hyperlend protocol.
Tidymodels MCP Server
An MCP server for accessing tidymodels GitHub information and generating code.
Lilith Shell
Execute terminal commands through a secure shell interface using an AI assistant.
MCP Reasoner
A reasoning engine with multiple strategies, including Beam Search and Monte Carlo Tree Search.
D2 MCP Server
Generate, render, and manipulate D2 diagrams with incremental editing capabilities.
AI Sessions
Searching and access your AI coding sessions from Claude Code, Gemini CLI, opencode, and OpenAI Codex.