Allows generating LLM-powered summaries of Federal Register rules using OpenAI's API.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fedreg-mcpSearch for recent EPA rules on chemical safety"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
fedreg-mcp
MCP server that gives AI agents first-class access to U.S. Federal Register rules and Regulations.gov public comments.
Built by Tool Factory — Tool #1.
🌐 Live: https://fedreg-mcp.vercel.app
🔌 MCP endpoint: https://fedreg-mcp.vercel.app/api/mcp (Streamable HTTP, stateless, no auth)
What it does
Lets an agent (Claude, Cursor, ChatGPT, Goose, etc.) answer questions like:
"What climate-disclosure rules has the SEC published this year?"
"Show me all FDA proposed rules with open comment periods."
"Which Federal Register rules under 40 CFR were finalized in the last 30 days?"
"Summarize document 2026-10643 for an executive audience."
"List rules from the DOT in the last 14 days, only final rules."
Related MCP server: moltawards-mcp
Tools
Tool | What it does | Notes |
| Query + agency + stage + date + CFR + pagination over Federal Register | Fuzzy agency resolution (EPA, FDA, SEC, etc.) |
| Full canonical record for a rule by document number | Includes source URLs incl. raw-text |
| Recent docs from an agency / across the gov't | Same envelope as |
| Public comments on a Regulations.gov docket | Requires free |
| Executive / legal / technical summary with citations | Requires |
Install
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"fedreg": {
"url": "https://fedreg-mcp.vercel.app/api/mcp"
}
}
}Claude Code
claude mcp add --transport http fedreg https://fedreg-mcp.vercel.app/api/mcpCursor
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in your project):
{
"mcpServers": {
"fedreg": {
"url": "https://fedreg-mcp.vercel.app/api/mcp"
}
}
}Local dev
npm install
cp .env.example .env.local # optional: REGULATIONS_GOV_API_KEY, OPENROUTER_API_KEY
npm run dev # landing page on http://localhost:5173
vercel dev # full stack incl. /api/* routesSmoke scripts (live, no env vars needed):
npx tsx scripts/smoke-fedreg.ts
npx tsx scripts/smoke-normalize.tsStack
TypeScript + Vercel serverless functions
@modelcontextprotocol/sdkv1.0.4 over Web-Standard Streamable HTTPVite + React for the landing page
Zod for tool schemas
tiny-lrufor in-memory cachingOpenRouter (or OpenAI) for the summarization tool
Data sources
federalregister.gov API v1 — no auth
regulations.gov API v4 — free key from api.data.gov
Privacy
We log structured, anonymized tool-call shapes ({ tool, args_shape, latency_ms, status, correlation_id }) — never raw query text, never PII. Used to learn what tools to build next.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mehtaphysical13/fedreg-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
