synapse-mcp

synapse-mcp

A Model Context Protocol (MCP) server that enables AI agent access to Synapse entities such as Datasets, Projects, Folders, Files, Tables, and more.

Category
访问服务器

README

Synapse MCP Server

synapse_wordmark

A Model Context Protocol (MCP) server that enables AI agent access to Synapse entities (Datasets, Projects, Folders, Files, Tables, and more).

You (your AI agent) can:

  • Retrieve entities by ID
  • Get entity annotations
  • List entity children
  • Search Synapse entities with path and type filters
  • Inspect provenance/activity recorded for an entity version

Available Tools

Tool Friendly Name Description
get_entity(entity_id) Fetch Entity Fetch core metadata for a Synapse entity by ID.
get_entity_annotations(entity_id) Fetch Entity Annotations Return custom annotations associated with an entity.
get_entity_provenance(entity_id, version=None) Fetch Entity Provenance Retrieve provenance (activity) metadata for an entity, optionally scoped to a specific version.
get_entity_children(entity_id) List Entity Children List children for container entities such as projects and folders.
search_synapse(query_term=None, ...) Search Synapse Search Synapse entities by keyword with optional name/type/parent filters. Results are provided by Synapse as data custodian; attribution and licensing follow the source entity metadata.

Available Resources

Resources provide ready-to-present context that clients can pull without extra parameters. When you need to search or compute derived results, prefer tools instead.

Resource Friendly Name Description
synapse://feeds/blog Sage Blog RSS Live RSS XML for the latest Sage Bionetworks publication posts.

⚠️ Terms of Service Compliance Notice

Important: When using this MCP server with external AI services (such as Claude, ChatGPT, or other cloud-based models), please be aware that:

  • You will use your personal Synapse access token to retrieve data
  • Data sent to external AI services may be stored, logged, or used for model training
  • The Synapse Terms of Service prohibit redistribution of data, which may include storage or use by third-party AI providers

Recommended Safe Usage:

  • ✅ Use with enterprise AI deployments with data residency guarantees
  • ✅ Use with local/self-hosted AI models
  • ✅ Leverage responsible AI use training if provided
  • ❌ Avoid use with consumer AI services that may store or train on your data

You are responsible for ensuring your usage complies with the Synapse Terms of Service.

Getting Started

The Synapse MCP server can be used as a remote hosted server (recommended) or installed locally from source. Choose the approach that fits your needs.

Remote Server (Recommended)

The hosted server is available at:

https://mcp.synapse.org/mcp

Authentication uses OAuth2 -- your MCP client will open a browser window for you to log in to Synapse. No API keys or tokens to manage.

Below are setup instructions for popular AI clients. If your client is not listed, use the generic JSON config.

Generic MCP JSON Config

Most MCP-compatible clients accept a JSON configuration block. Add the following to your client's MCP config file:

{
  "mcpServers": {
    "synapse": {
      "url": "https://mcp.synapse.org/mcp",
      "type": "http"
    }
  }
}

Claude Desktop

Go to Settings > Connectors > Add custom connector and enter the URL https://mcp.synapse.org/mcp.

<img width="664" height="146" alt="Claude Desktop connector setup" src="https://github.com/user-attachments/assets/fcfe54ba-1c1c-4fa8-9bae-c198cffff6ce" />

Claude Code (CLI)

claude mcp add --transport http synapse -- https://mcp.synapse.org/mcp

VS Code / GitHub Copilot

VS Code's MCP client does not yet fully support OAuth Dynamic Client Registration (DCR). To connect to the remote server, follow these steps:

Step 1: Register a client

Run this command once to register an OAuth client with the MCP server:

curl -X POST https://mcp.synapse.org/register \
  -H "Content-Type: application/json" \
  -d '{
    "client_name": "vscode-synapse",
    "redirect_uris": ["http://127.0.0.1"],
    "grant_types": ["authorization_code", "refresh_token"],
    "response_types": ["code"],
    "token_endpoint_auth_method": "none"
  }'

Save the client_id from the response (e.g., c3dfaf80-126c-4f46-80ab-114747fcc3b3).

Step 2: Configure VS Code

Create or edit .vscode/mcp.json in your workspace:

{
  "servers": {
    "synapse": {
      "url": "https://mcp.synapse.org/mcp",
      "type": "http"
    }
  }
}

Step 3: Complete the OAuth flow

When you start the server, VS Code will open a browser to an authorization URL. Replace the client_id value in the URL with your registered client_id from Step 1, then press Enter to continue the Synapse login flow.

For example, change client_id=100441 to client_id=YOUR_CLIENT_ID in the browser address bar.

Alternatively, you can use the Local Server setup with a Personal Access Token, which does not require OAuth.

Cursor

Add to Cursor Settings > MCP > + Add new global MCP server, or add to your project's .cursor/mcp.json:

{
  "mcpServers": {
    "synapse": {
      "url": "https://mcp.synapse.org/mcp",
      "type": "http"
    }
  }
}

Local Server

Run the server locally for development, self-hosting, or offline use. The local server uses stdio transport by default, which is what most MCP clients expect for command-based servers.

Note: synapse-mcp is not currently published on PyPI. You must install from source.

Install

git clone https://github.com/Sage-Bionetworks/synapse-mcp.git
cd synapse-mcp
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -e .

After installation, the synapse-mcp command is available in your virtual environment.

Authentication for Local Server

For local use, authenticate with a Synapse Personal Access Token (PAT) by setting the SYNAPSE_PAT environment variable:

export SYNAPSE_PAT="your_synapse_pat_here"

To create a PAT, visit your Synapse Personal Access Tokens page.

MCP Client Configuration (Local)

Important: The synapse-mcp command must be on your PATH. If you installed in a virtual environment, either activate it first or use the full path to the binary (e.g., /path/to/.venv/bin/synapse-mcp).

Generic JSON config (stdio):

{
  "mcpServers": {
    "synapse": {
      "command": "/path/to/.venv/bin/synapse-mcp",
      "env": {
        "SYNAPSE_PAT": "your_synapse_pat_here"
      }
    }
  }
}

Claude Code (local):

claude mcp add synapse -e SYNAPSE_PAT=your_synapse_pat_here -- /path/to/.venv/bin/synapse-mcp

VS Code / GitHub Copilot (local):

In .vscode/mcp.json:

{
  "servers": {
    "synapse": {
      "command": "/path/to/.venv/bin/synapse-mcp",
      "env": {
        "SYNAPSE_PAT": "your_synapse_pat_here"
      }
    }
  }
}

Cursor (local):

{
  "mcpServers": {
    "synapse": {
      "command": "/path/to/.venv/bin/synapse-mcp",
      "env": {
        "SYNAPSE_PAT": "your_synapse_pat_here"
      }
    }
  }
}

Configuration

Environment Selection

You can configure which Synapse platform instance to connect to by setting the SYNAPSE_ENV environment variable:

  • prod (default) -- Production instance at synapse.org
  • staging -- Staging instance at staging.synapse.org
  • dev -- Development instance at dev.synapse.org

If not set, the server defaults to prod.

Authentication

Method When to Use How
OAuth2 (default) Remote server, production use Browser-based login -- no setup needed
Personal Access Token Local development, CI/CD, headless environments Set SYNAPSE_PAT environment variable

For contributor/development setup details, see DEVELOPMENT.md.

Example Prompts

See usage examples

Contributing

Contributions are welcome! Please see our Development Guide for instructions on setting up a development environment, running tests, and more.

License

MIT

Contact

synapse_icon

For issues, please file an issue. For other contact, see https://sagebionetworks.org/contact.

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