CEDAR MCP Server

CEDAR MCP Server

Enables interaction with the CEDAR metadata repository, including fetching templates, searching BioPortal ontology terms, and managing template instances.

Category
访问服务器

README

CEDAR MCP Server

A Model Context Protocol (MCP) server for interacting with the CEDAR (Center for Expanded Data Annotation and Retrieval) metadata repository.

Prerequisites

Before using this MCP server, you'll need API keys from:

CEDAR API Key

BioPortal API Key

Running the CEDAR MCP Server

Set your API keys as environment variables:

export CEDAR_API_KEY="your-cedar-key"
export BIOPORTAL_API_KEY="your-bioportal-key"

Option 1: Using UVX (Recommended)

Run directly without installation using uvx:

uvx cedar-mcp

Option 2: Using pip

Install from PyPI and run:

pip install cedar-mcp
cedar-mcp

Note: The --cedar-api-key and --bioportal-api-key CLI flags are deprecated and will be removed in a future release. Use environment variables instead.

Transport Options

By default, the server uses stdio transport. You can also run it as an HTTP server using SSE or streamable-http transports:

# SSE transport on default host/port (127.0.0.1:8000)
cedar-mcp --transport sse

# Streamable HTTP on custom host/port
cedar-mcp --transport streamable-http --host 0.0.0.0 --port 9000
Flag Choices Default Description
--transport stdio, sse, streamable-http stdio Transport protocol
--host 127.0.0.1 Host to bind to (HTTP transports only)
--port 8000 Port to bind to (HTTP transports only)

Using with Claude Code

Add the CEDAR MCP server to Claude Code:

claude mcp add cedar-mcp --uvx -e CEDAR_API_KEY=your-cedar-key -e BIOPORTAL_API_KEY=your-bioportal-key

Using with Claude Desktop

To use with Claude Desktop app:

  1. Install the MCP server using one of the methods above
  2. Add to Claude Desktop configuration in your claude_desktop_config.json:
{
  "mcpServers": {
    "cedar-mcp": {
      "command": "uvx",
      "args": [
        "cedar-mcp"
      ],
      "env": {
        "CEDAR_API_KEY": "your-cedar-key",
        "BIOPORTAL_API_KEY": "your-bioportal-key",
        "CEDAR_MCP_CACHE_TTL_SECONDS": "86400",
        "CEDAR_MCP_CACHE_DIR": "/path/to/custom/location"
      }
    }
  }
}

Or if you have it installed locally:

{
  "mcpServers": {
    "cedar-mcp": {
      "command": "cedar-mcp",
      "env": {
        "CEDAR_API_KEY": "your-cedar-key",
        "BIOPORTAL_API_KEY": "your-bioportal-key",
        "CEDAR_MCP_CACHE_TTL_SECONDS": "86400",
        "CEDAR_MCP_CACHE_DIR": "/path/to/custom/location"
      }
    }
  }
}

The CEDAR_MCP_CACHE_TTL_SECONDS and CEDAR_MCP_CACHE_DIR environment variables are optional. When set under the "env" key, Claude Desktop injects them into the server process environment before it starts, so the cache picks them up automatically. If omitted, the defaults apply (24-hour TTL and a platform-specific cache directory — see Cache Configuration).

Available Tools

Here is the list of CEDAR tools with a short description

  • get_cedar_template: Fetches a template from the CEDAR repository.
  • get_instances_based_on_template: Gets template instances that belong to a specific template with pagination support.
  • term_search_from_branch: Searches BioPortal for standardized ontology terms within a specific branch.
  • term_search_from_ontology: Searches BioPortal for standardized ontology terms within an entire ontology.
  • get_branch_children: Fetches all immediate children terms for a given branch in an ontology.
  • get_ontology_class_tree: Fetches the hierarchical tree structure for a given class in an ontology.
  • remove_stale_cache_entries: Removes expired entries from the BioPortal search cache.
  • clear_bioportal_cache: Clears all entries from the BioPortal search cache.

Cache Configuration

BioPortal search results are cached locally using SQLite to reduce latency and API load. The cache persists across server restarts.

Variable Default Description
CEDAR_MCP_CACHE_TTL_SECONDS 86400 (24 hours) Time-to-live for cached BioPortal responses
CEDAR_MCP_CACHE_DIR Platform-specific (see below) Override the cache directory location

Default cache locations:

  • macOS: ~/Library/Caches/cedar-mcp
  • Linux: $XDG_CACHE_HOME/cedar-mcp or ~/.cache/cedar-mcp
  • Windows: %LOCALAPPDATA%/cedar-mcp/cache

Development

Install Development Dependencies

pip install -r requirements-dev.txt

Running Tests

This project includes comprehensive integration tests that validate real API interactions with both CEDAR and BioPortal APIs.

For detailed testing information, see test/README.md.

Contributing

Contributions are welcome! Please ensure all tests pass before submitting a Pull Request:

python run_tests.py --integration

License

This project is licensed under the MIT License — see the LICENSE file for details.

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