Connect eCFR to Codex
Query eCFR 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 eCFR API, the continuously updated electronic version of the US Code of Federal Regulations maintained by the Office of the Federal Register and GPO. Where the Federal Register tells you what is changing, the eCFR is the codified text that results - the regulation as it stands today.
Key features:
- search_regulations: full-text search across all 50 CFR titles, returning the title/part/section citation of each hit with a highlighted excerpt, optionally restricted to one title.
- get_section_text: read the actual regulation text by citation (e.g. title 40, part 50, section 50.1). Without a section number it lists the part's section headings so you can drill in. A date parameter gives you the text as it stood on a past date - useful for point-in-time compliance questions.
- list_titles: the 50 titles with their subjects, last-amended dates and how current the eCFR text is.
The upstream API only serves regulation bodies as XML; this server converts them to plain text, and truncates very long sections rather than overflowing your context. Pair it with the Federal Register server: find a rulemaking there, then read the consolidated result here.
No API key is needed, and the content is US government work in the public domain.
How to connect eCFR to Codex
- 1
In the Arlet dashboard, open Data tools, find eCFR 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.