mcp
by gavelin-ai
A hosted Model Context Protocol server that lets AI assistants search US state bills and hearing transcripts with named speakers. This repository holds only the documentation and configuration for connecting to the Gavelin service.
- Stars
- 1
- Licence
- MIT
- Runs on
- A cloud service
- Setup
- Easy
- Language
- JavaScript
- Age
- 223 days
What you can do with it
- Search bills across all 50 states and DC by keyword, sponsor, committee or status
- Find what a named legislator or witness said in hearings on a topic
- Pull the full labelled transcript of a committee hearing
Make money with it
A freelancer could offer regular state-legislation briefings or monitoring reports to trade groups and small firms, using the tool to do the research quickly.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Monitor state bills and hearing testimony that affect your industry without paying for a tracking service
- Prepare policy briefings or client updates quickly by summarising what legislators said on a topic
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Add it to Claude Code
claude mcp add --transport http mcp https://mcp.gavelin.ai/mcp
This one runs on the maker's server, not your computer, so what you send it leaves your machine.
From the official MCP Registry (ai.gavelin/mcp). Only connect MCP servers you trust: they can act on your behalf.
Getting it running
Sign up at gavelin.ai for a free API key, then add the server URL and bearer token to your MCP client's config file.
Follow the official instructions in the project README.
Things to check
- The server itself is proprietary and hosted; the MIT licence covers only the documentation
- Needs an API key and is rate-limited on the free tier
- Hearing transcripts cover only a growing number of states, not all 50
- Very new project with minimal community adoption
Checked 03 Nov 2026. Summary drafted by AI from the project's README.