nf-core 파이프라인 저장소를 관리하고 탐색하기 위한 MCP 서버입니다.
로컬 nf-core 저장소(rnaseq, sarek, 모듈, 도구) 나열
파이프라인 구성 및 워크플로에 액세스
파이프라인 파일 검색
파이프라인 모듈 탐색
Related MCP server: pipen-mcp
지엑스피1
# 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-mcp작업 공간에 새로운 nf-core 파이프라인 저장소를 추가하려면:
저장소를 복제합니다 .
# 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 manage디렉토리 구조 : 작업 공간은 다음과 같습니다.
workspace/
├── rnaseq/
├── sarek/
├── modules/
└── your-new-pipeline/설치 확인 : MCP 서버를 시작한 후 list-pipelines 명령을 사용하여 새 파이프라인이 감지되었는지 확인합니다.
list-pipelines참고: MCP 서버는 작업 공간 디렉토리에 있는 모든 nf-core 파이프라인 저장소를 자동으로 감지하고 관리합니다.
list-pipelines
작업 공간의 모든 nf-core 파이프라인을 나열합니다.
구성 파일 상태를 표시합니다
매개변수가 필요하지 않습니다
get-pipeline-modules
파이프라인에서 모듈 정보를 가져옵니다.
매개변수:
pipeline : 파이프라인 이름(rnaseq, sarek 또는 모듈)
search-pipelines
파이프라인 파일을 검색합니다
매개변수:
query : 검색 쿼리
pipeline (선택 사항): 검색할 특정 파이프라인
pipeline-config
파이프라인 구성을 가져옵니다
URI 형식: pipeline://{name}/config
매개변수:
name : 파이프라인 이름(rnaseq, sarek 또는 모듈)
pipeline-workflow
파이프라인 워크플로를 가져옵니다.
URI 형식: pipeline://{name}/workflow
매개변수:
name : 파이프라인 이름(rnaseq, sarek 또는 모듈)
mcp.json 에 다음을 추가하세요.
{
"mcpServers": {
"nf-core": {
"command": "npx",
"args": ["-y", "nf-core-mcp"]
}
}
}mcp.json 에 다음을 추가하세요.
{
"mcpServers": {
"nf-core": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"/path/to/your/workspace:/app/workspace",
"nf-core-mcp"
]
}
}
}Cursor에서 MCP 서버 사용:
# 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
| Name | Required | Description | Default |
|---|---|---|---|
| pipeline | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| pipeline | No | ||
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get-pipeline-moduleslist-pipelinessearch-pipelinesScored across 3 tools
The three tools have clearly distinct purposes: get-pipeline-modules retrieves modules for a specific pipeline, list-pipelines enumerates available pipelines, and search-pipelines finds pipelines based on criteria. There is no overlap in functionality, making tool selection straightforward for an agent.
All tool names follow a consistent verb-noun pattern with hyphens (e.g., get-pipeline-modules, list-pipelines, search-pipelines). The naming is uniform and predictable, using clear action verbs paired with relevant nouns.
With only three tools, the server feels thin for a pipeline management domain, potentially lacking operations like create, update, or delete pipelines. However, the tools cover basic discovery and inspection, which might be sufficient for a limited scope.
The toolset is severely incomplete for pipeline management, missing essential CRUD operations such as creating, updating, or deleting pipelines. It only supports discovery and inspection, leaving significant gaps that could hinder agent workflows.
Manage repositories, users, releases, and automate GitHub workflows
Dive into the world of open-source with the GitHub Repo Explorer! Utilize the powerful GitHub
Access the GitHub API, enabling file operations, repository management, search functionality, and…
Create, browse, remix, collaborate on, and run durable AI workflow nodes from MCP hosts.
