连接能力
wjlim nf core mcp 为 AI Agent 提供什么
- List local nf-core repositories (rnaseq, sarek, modules, tools)
- Access pipeline configurations and workflows
- Search through pipeline files
- Explore pipeline modules
- **Clone the repositories**:
- **Directory Structure**:
- **Verify Installation**:
安全
MCP 收录不等于安全审核
MCP 服务器可能获得模型上下文、凭据、本地文件或调用外部系统的权限。连接 Agent 前,请检查代码、环境变量、网络行为、软件包来源与维护状态。
README
仓库文档
An MCP server for managing and navigating nf-core pipeline repositories.
- List local nf-core repositories (rnaseq, sarek, modules, tools)
- Access pipeline configurations and workflows
- Search through pipeline files
- Explore pipeline modules
cd nf-core_mcp
npm install
# Build TypeScript
npm run build
# Start the server
npm start# 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-mcpTo 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.
-
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
-
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)
Add the following to your mcp.json:
{
"mcpServers": {
"nf-core": {
"command": "npx",
"args": ["-y", "nf-core-mcp"]
}
}
}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"
]
}
}
}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
# If installed globally
nf-core-mcp
# If installed locally
npx nf-core-mcp
# Using npx without installation
npx -y nf-core-mcpdocker run -it --rm \
-v /path/to/your/workspace:/app/workspace \
nf-core-mcp# Install dependencies
npm install
# Build TypeScript
npm run build
# Run in development mode
npm run dev
# Run tests
npm test
# Run linter
npm run lintMIT
社区
收藏、评分与讨论
正在载入社区数据…