What do I need to run this server?
You need a Congress.gov API key (obtained from https://api.data.gov/signup/), Node.js, and npm. The key is stored in a `.env` file.
@bsmi021
基本信息
This is a Model Context Protocol (MCP) server designed to provide access to the official Congress.gov API (v3) using a hybrid approach.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Congress.gov API MCP Server is a Model Context Protocol (MCP) server that provides access to the official Congress.gov API (v3). It uses MCP Resources for direct lookups of core legislative entities (Bills, Members, Congresses, Committees, general Info) via standardized URIs, and MCP Tools for complex searches and retrieving related data lists. It is designed for MCP clients like AI assistants or development tools needing U.S. legislative data.
Install dependencies with npm install, add your Congress.gov API key to a .env file as CONGRESS_GOV_API_KEY, build with npm run build, and run with npm start. Connect an MCP client via stdio to the running server. Access resources using access_mcp_resource with URIs like congress-gov://bill/117/hr/3076. Use tools congress_search and congress_getSubResource in a required two-step process: first find an entity ID via search, then fetch related data using that ID.
You need a Congress.gov API key (obtained from https://api.data.gov/signup/), Node.js, and npm. The key is stored in a `.env` file.
First, use `congress_search` to find an entity (e.g., a member) and get its ID. Second, use `congress_getSubResource` with that ID to retrieve related data like sponsored legislation. This is mandatory because related data requires a valid parent URI.
No. The Congress.gov API does not support filtering general searches (e.g., for bills or members) by congress using the `filters` parameter. Congress-specific filtering requires API paths that `congress_search` does not construct.
The server will return an error. You must use a `subResource` string that is strictly valid for the `parentUri` type (e.g., `'sponsored-legislation'` for members, `'actions'` for bills).
The server includes a rate limit service (likely respecting the Congress.gov API’s own limits). The README does not specify a hard limit, but the server is designed to handle rate limiting gracefully.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
评论