Federal Register MCP Server
Enables AI assistants to search and retrieve executive orders, presidential documents, rules, and agency information from the Federal Register API through natural language queries.
README
Federal Register MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to the Federal Register API. This enables searching and retrieving executive orders, presidential documents, rules, and agency information.
What is MCP?
MCP is a protocol that allows AI assistants like Claude to interact with external tools and data sources. This server exposes Federal Register data as a set of tools that can be called by AI assistants.
Features
- Executive Orders: Search, retrieve, and get full text of executive orders by president, year, date range, or keyword
- Presidential Documents: Search memoranda and proclamations
- Federal Register Documents: Search and retrieve any document type (rules, proposed rules, notices)
- Agency Information: List all federal agencies or get details about specific agencies
- Public Inspection: View documents before official publication
Roadmap
- Hosted version - Deploy a public instance so users can connect without running locally
- Legislation tracking - Integrate Congress.gov API and Open States for federal and state legislation
- Enriched metadata - Add categories, correlations between executive orders and legislation, impacted populations, and other analytical data
- UI experience - Leverage OpenAI Apps to provide a visual interface for exploring executive and legislative data
Installation
# Clone the repository
git clone https://github.com/yourusername/federal-register-mcp.git
cd federal-register-mcp
# Install dependencies
npm install
# Build TypeScript
npm run build
Usage
This server supports two transport modes:
| Mode | Transport | Use Case |
|---|---|---|
| stdio (default) | Standard I/O | Claude Desktop (local) |
| http | Streamable HTTP | Claude Code, ChatGPT, remote clients |
Claude Desktop (stdio mode)
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"federal-register": {
"command": "node",
"args": ["/path/to/federal-register-mcp/dist/server.js"]
}
}
}
Claude Code (stdio or HTTP mode)
Option 1: stdio (local)
{
"mcpServers": {
"federal-register": {
"command": "node",
"args": ["/path/to/federal-register-mcp/dist/server.js"]
}
}
}
Option 2: HTTP (local or remote)
Start the server in HTTP mode:
npm run start:http
Then configure Claude Code to connect to the HTTP endpoint:
{
"mcpServers": {
"federal-register": {
"url": "http://localhost:3000/mcp"
}
}
}
ChatGPT (HTTP mode, requires public URL)
ChatGPT cannot connect to localhost. You need to expose the server publicly:
Option 1: ngrok (for development)
# Terminal 1: Start the server
npm run start:http
# Terminal 2: Create a tunnel
ngrok http 3000
Then use the ngrok URL (e.g., https://abc123.ngrok.io/mcp) in ChatGPT.
Option 2: Deploy to a cloud host (for production)
Deploy to any HTTPS-capable host:
- Cloudflare Workers
- Fly.io
- Railway
- Vercel
- AWS / GCP / Azure
The MCP endpoint will be at https://your-host.com/mcp.
Running Directly
# stdio mode (default) - for Claude Desktop
npm start
# HTTP mode - for Claude Code, ChatGPT
npm run start:http
# HTTP mode with custom port
node dist/server.js --http --port 8080
# Or use environment variable
MCP_PORT=8080 npm run start:http
Development
# Edit files in src/*.ts, then build
npm run build
# Or use watch mode for auto-recompile
npm run dev
Health Check (HTTP mode)
When running in HTTP mode, a health endpoint is available:
curl http://localhost:3000/health
# {"status":"ok","mode":"http","sessions":0}
Available Tools
| Tool | Description |
|---|---|
search_executive_orders |
Search for executive orders by president, year, date range, or keyword |
get_executive_order |
Get a specific executive order by its EO number |
get_executive_order_full_text |
Fetch the complete full text of an executive order |
get_recent_executive_orders |
Get executive orders signed in the last 30 days |
search_documents |
Search all Federal Register documents with flexible filtering |
get_document |
Fetch a Federal Register document by its document number |
get_document_text |
Fetch the full plain text content of a document |
search_presidential_memoranda |
Search for presidential memoranda |
search_proclamations |
Search for presidential proclamations |
get_public_inspection_documents |
Get documents currently on public inspection |
get_agencies |
Get a list of all federal agencies |
get_agency |
Get detailed information about a specific agency |
Example Queries
Once configured, you can ask Claude questions like:
- "What executive orders has Joe Biden signed about climate change?"
- "Show me Trump's executive orders from his second term (2025)"
- "Get the full text of Executive Order 14067"
- "What documents are on public inspection today?"
- "Find all proposed rules from the EPA in 2024"
API Reference
This server uses the Federal Register API v1. The API is free and requires no authentication.
Project Structure
federal-register-mcp/
├── src/
│ ├── server.ts # MCP server implementation
│ └── federal-register-api.ts # Federal Register API client
├── dist/ # Compiled JavaScript (generated)
├── tsconfig.json
├── package.json
└── README.md
License
MIT License - see LICENSE for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。