Skip to main content
Glama
enesjakozh
wjlim

nf-core MCP Server

by wjlim
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

nf-core MCP サーバー

nf-core パイプライン リポジトリを管理およびナビゲートするための MCP サーバー。

特徴

  • ローカル nf-core リポジトリ (rnaseq、sarek、モジュール、ツール) を一覧表示します

  • パイプライン構成とワークフローにアクセスする

  • パイプラインファイルを検索する

  • パイプラインモジュールを探索する

Related MCP server: pipen-mcp

インストール

NPMバージョン


cd nf-core_mcp
npm install

# Build TypeScript
npm run build

# Start the server
npm start

Dockerバージョン

# 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

nf-coreリポジトリの追加

新しい nf-core パイプライン リポジトリをワークスペースに追加するには:

  1. リポジトリをクローンします:

    # 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

  2. ディレクトリ構造: ワークスペースは次のようになります。

    workspace/
├── rnaseq/
├── sarek/
├── modules/
└── your-new-pipeline/

  3. インストールの確認: MCP サーバーを起動した後、 list-pipelinesコマンドを使用して、新しいパイプラインが検出されていることを確認します。

    list-pipelines

注: MCP サーバーは、ワークスペース ディレクトリ内のすべての nf-core パイプライン リポジトリを自動的に検出して管理します。

利用可能なツール

  1. list-pipelines

    • ワークスペース内のすべての nf-core パイプラインを一覧表示します

    • 設定ファイルのステータスを表示します

    • パラメータは必要ありません

  2. get-pipeline-modules

    • パイプラインからモジュール情報を取得します

    • パラメータ:

      • pipeline : パイプライン名 (rnaseq、sarek、または modules)

  3. search-pipelines

    • パイプラインファイルを検索する

    • パラメータ:

      • query : 検索クエリ

      • pipeline （オプション）: 検索する特定のパイプライン

利用可能なリソース

  1. pipeline-config

    • パイプライン構成を取得する

    • URI 形式: pipeline://{name}/config

    • パラメータ:

      • name : パイプライン名 (rnaseq、sarek、または modules)

  2. pipeline-workflow

    • パイプラインワークフローを取得する

    • URI 形式: pipeline://{name}/workflow

    • パラメータ:

      • name : パイプライン名 (rnaseq、sarek、または modules)

カーソルIDEでの使用

NPXの使用（推奨）

mcp.jsonに次のコードを追加します。

{
  "mcpServers": {
    "nf-core": {
      "command": "npx",
      "args": ["-y", "nf-core-mcp"]
    }
  }
}

Dockerの使用

mcp.jsonに次のコードを追加します。

{
  "mcpServers": {
    "nf-core": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/path/to/your/workspace:/app/workspace",
        "nf-core-mcp"
      ]
    }
  }
}

使用例

カーソルで MCP サーバーを使用する:

# 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

サーバーの実行

NPMの使用

# If installed globally
nf-core-mcp

# If installed locally
npx nf-core-mcp

# Using npx without installation
npx -y nf-core-mcp

Dockerの使用

docker run -it --rm \
  -v /path/to/your/workspace:/app/workspace \
  nf-core-mcp

発達

# 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

ライセンス

マサチューセッツ工科大学

Available Tools

3 tools
get-pipeline-modulesD
NameRequiredDescriptionDefault
pipelineYes

TDQS

D1/5.0
Behavior1/5

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.

Conciseness1/5

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.

Completeness1/5

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.

Parameters1/5

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.

Purpose1/5

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.

Usage Guidelines1/5

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.

list-pipelinesD
NameRequiredDescriptionDefault

No parameters

TDQS

D1/5.0
Behavior1/5

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.

Conciseness1/5

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.

Completeness1/5

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.

Parameters1/5

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.

Purpose1/5

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.

Usage Guidelines1/5

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.

search-pipelinesD
NameRequiredDescriptionDefault
pipelineNo
queryYes

TDQS

D1/5.0
Behavior1/5

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.

Conciseness1/5

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.

Completeness1/5

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.

Parameters1/5

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.

Purpose1/5

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.

Usage Guidelines1/5

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.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observedget-pipeline-modules
    • First observedlist-pipelines
    • First observedsearch-pipelines
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

D1.8/5.0

Scored across 3 tools

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count3/5

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.

Completeness2/5

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.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches