Connect Federal Register to Codex
Query Federal Register directly from Codex. Arlet links the two through one MCP connection and takes care of API keys.
This server connects your AI client to the Federal Register API, the official daily journal in which US federal agencies publish rules, proposed rules and notices. It is the primary source for tracking American regulatory activity.
Key features:
- search_documents: search by full-text term, document type (final rule, proposed rule, notice, presidential document), issuing agency and publication-date range. Use it to answer what a regulator has recently published on a topic.
- get_document: fetch one document's full record - effective date, comment deadline, affected CFR references, regulation identifier number (RIN), docket ids, and links to the full text and the comment page.
- list_agencies: resolve an agency acronym or name to the slug the search endpoint filters by, so 'EPA' becomes environmental-protection-agency.
The combination of the comment deadline and the proposed-rule filter makes this useful for compliance monitoring: you can find which proposals are still open for comment and when they close. For the codified text that these rules amend, pair this server with the eCFR server.
No API key is needed, and the content is US government work in the public domain.
How to connect Federal Register to Codex
- 1
In the Arlet dashboard, open Data tools, find Federal Register and switch it on. No API key setup is needed.
- 2
In your terminal, run codex mcp add arlet --url https://mcp.arlet.dev/mcp/ to add Arlet as an MCP server.
- 3
Codex detects OAuth support and opens your browser. Sign in with Google and click Allow on the consent screen.
- 4
Once connected, both the CLI and the IDE extension can call Arlet tools (the configuration is shared).
If the browser does not open, run codex mcp login arlet to redo the authentication.
