NGS360 MCP Server

NGS360 MCP Server

Exposes the NGS360 bioinformatics platform REST API as MCP tools, enabling AI assistants to manage sequencing runs, projects, workflows, and more through natural language.

Category
访问服务器

README

NGS360 MCP Server

A Model Context Protocol (MCP) server that exposes the NGS360 REST API as tools for AI assistants.

Overview

This MCP server wraps the NGS360 bioinformatics platform API, providing tools for:

Domain Tools Description
Runs 14 tools Sequencing run CRUD, sample sheets, metrics, demultiplexing
Jobs 6 tools AWS Batch job submission, monitoring, and logs
Projects 11 tools Project CRUD, samples, pipeline actions, vendor ingestion
Files 7 tools File record management, S3 browsing
Search 1 tool Cross-index search (projects, runs, samples)
Workflows 11 tools Workflow identity, versions, aliases, deployments
Pipelines 5 tools Pipeline CRUD, workflow associations
QC Metrics 5 tools QC record creation, search, retrieval
Vendors 5 tools Vendor CRUD
Settings 3 tools Application settings management
Platforms 3 tools Workflow execution platform registry
Manifest 2 tools Manifest retrieval and validation

Installation

cd mcp-server
pip install -e .

Or with uv:

cd mcp-server
uv pip install -e .

Configuration

The server uses environment variables for configuration:

Variable Default Description
NGS360_API_URL http://localhost:8000 Base URL of the NGS360 API
NGS360_API_TOKEN (empty) Bearer token for authentication

Usage

Running directly

ngs360-mcp-server

With Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "ngs360": {
      "command": "ngs360-mcp-server",
      "env": {
        "NGS360_API_URL": "https://your-ngs360-api.example.com",
        "NGS360_API_TOKEN": "your-bearer-token"
      }
    }
  }
}

With VS Code / Roo

Add to your MCP settings:

{
  "mcpServers": {
    "ngs360": {
      "command": "ngs360-mcp-server",
      "env": {
        "NGS360_API_URL": "https://your-ngs360-api.example.com",
        "NGS360_API_TOKEN": "your-bearer-token"
      }
    }
  }
}

Development

Project Structure

mcp-server/
├── pyproject.toml
├── README.md
└── ngs360_mcp_server/
    ├── __init__.py
    ├── client.py          # HTTP client wrapper for the NGS360 API
    ├── server.py          # MCP server entry point
    └── tools/
        ├── __init__.py
        ├── runs.py        # Sequencing run tools
        ├── jobs.py        # Batch job tools
        ├── projects.py    # Project & sample tools
        ├── files.py       # File management tools
        ├── search.py      # Cross-index search tools
        ├── workflows.py   # Workflow management tools
        ├── pipelines.py   # Pipeline management tools
        ├── qcmetrics.py   # QC metrics tools
        ├── vendors.py     # Vendor management tools
        ├── settings.py    # Settings tools
        ├── platforms.py   # Platform registry tools
        └── manifest.py    # Manifest tools

Testing with MCP Inspector

npx @modelcontextprotocol/inspector ngs360-mcp-server

Adding New Tools

  1. Create or edit a file in ngs360_mcp_server/tools/
  2. Define a register_*_tools(mcp, client) function
  3. Register it in ngs360_mcp_server/server.py

Each tool is a decorated async function:

@mcp.tool()
async def my_new_tool(param1: str, param2: int = 10) -> dict:
    """Tool description shown to the AI assistant.

    Args:
        param1: Description of param1
        param2: Description of param2
    """
    return await client.get("/my/endpoint", params={"p": param1})

API Coverage

This MCP server covers the full NGS360 API surface at /api/v1/*:

  • POST/GET /runs — Create and list sequencing runs
  • GET/PUT /runs/{run_id} — Get/update a run
  • GET /runs/{run_id}/samplesheet — Sample sheet
  • GET /runs/{run_id}/metrics — Demux metrics
  • GET/POST /runs/demultiplex — Demux workflows
  • POST/GET/DELETE /runs/{run_id}/samples — Sample associations
  • POST/GET /jobs — Submit and list batch jobs
  • GET/PUT /jobs/{job_id} — Get/update job
  • GET /jobs/{job_id}/log — Job logs
  • POST/GET /projects — Create and list projects
  • GET/PUT/PATCH /projects/{project_id} — Project CRUD
  • POST/GET /projects/{project_id}/samples — Project samples
  • POST /projects/{project_id}/actions/submit — Pipeline submission
  • POST/GET /files — File record management
  • GET/PATCH/DELETE /files/{file_id} — File operations
  • GET /files/list — S3 browser
  • GET /search — Global search
  • POST/GET /workflows — Workflow identity
  • POST/GET /workflows/{id}/versions — Versions
  • PUT/GET/DELETE /workflows/{id}/aliases — Aliases
  • POST/GET/DELETE /workflows/.../deployments — Deployments
  • POST/GET /pipelines — Pipeline CRUD
  • POST/DELETE /pipelines/{id}/workflows — Workflow membership
  • POST/GET/DELETE /qcmetrics — QC records
  • GET/POST /qcmetrics/search — QC search
  • POST/GET/PUT/DELETE /vendors — Vendor management
  • GET/PUT /settings — Application settings
  • POST/GET /platforms — Platform registry
  • GET/POST /manifest — Manifest operations

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选