mcpField
N
Nf-core tools MCP (Unofficial)

Nf-core tools MCP (Unofficial)

Local
github.com/FloWuenneScience & Education1Updated 81w ago
Repository

About Nf-core tools MCP (Unofficial)

Nf-core tools MCP (Unofficial) is an experimental MCP server for nf-core tools and pipeline or module workflows. It offers implementations using either the command line or the Python package.

Key features

  1. 01Create pipelines from the nf-core template
  2. 02List nf-core modules
  3. 03Create modules from the template
  4. 04Install modules into a pipeline or repository
  5. 05CLI and Python implementations

Use cases

  1. 01Start an nf-core pipeline
  2. 02Find available nf-core modules
  3. 03Add a module to a pipeline or repository

MCP support

It exposes nf-core pipeline and module operations as tools for MCP clients, with separate CLI-based and Python-based server implementations.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Nf-core tools MCP (Unofficial)

A repo to experiment with MCP capabilities for nf-core tools functions.

Overview

This MCP provides a suite of tools for accessing nf-core tools for pipelines and modules:

  • Create a pipeline using the nf-core template
  • List nf-core modules
  • Create a module using the nf-core modules template
  • Install existing nf-core modules into your pipeline or modules repo

For testing purposes, tools were implemented from the command line (cli) and directly from the python package (python). Two different MCP server files exist for these two implementations:

  1. nf-core.test-server.cli.py
  2. nf-core.test-server.python.py

Installation

Installing with FastMCP to use in Claude Desktop
  1. Create a venv with uv:
uv venv
  1. Activate the environment:
source .venv/bin/activate
  1. Add required packages:
uv add "mcp[cli]" nf-core
  1. Install the server
fastmcp install nf-core.test-server.cli.py ## CLI server
fastmcp install nf-core.test-server.python.py ## Python based server
Adding server to Cursor
{
  "mcpServers": {
    "mix_server": {
      "command": "uv",
      "args": [
        "--directory",
        "[Full path to the server directory (this repo folder)]]",
        "run",
        "server.py"
      ]
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.