What is fedreg-mcp-server CLAUDE.md?

A project guide for Claude Code working on a server that accesses three U.S. government regulation databases: the Federal Register, the electronic Code of Federal Regulations, and Regulations.gov. It explains the available commands, setup, tests, and build process.

It is for developing a tool that searches and runs queries against U.S. federal regulations data.

It tells the coding agent how the repository is organized and how to check changes with its TypeScript type checker, tests, linter, and build command.

How blen-labs/fedreg-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to blen-labs/fedreg-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/blen-labs/fedreg-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/blen-labs/fedreg-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/blen-labs/fedreg-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/blen-labs/fedreg-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/blen-labs/fedreg-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/blen-labs/fedreg-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/blen-labs/fedreg-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/blen-labs/fedreg-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,728 This file is loaded in full into every session.

When invoked 3,728 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.03728	$0.03728
Opus 5.5	$0.01491	$0.01491
Sonnet 5.5	$0.00746	$0.00746
Haiku 4.5	$0.00373	$0.00373

Measured today against content hash 7c3c9d641f88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fedreg-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

@blen/fedreg-mcp-server — a "code-mode" MCP server for three U.S. government APIs: Federal Register (fr.*), eCFR (ecfr.*), and regulations.gov (regs.*). Instead of dozens of narrow tools it exposes exactly three — search_api, describe_schema, execute — and lets the model write JavaScript that runs in a locked-down sandbox with one global per source. Transports: stdio (default) and Streamable HTTP (--http).

Commands

Run everything from this directory ([email protected] pinned via packageManager; Node >= 20.19):

pnpm install
pnpm typecheck                          # tsc --noEmit — THE correctness gate; covers src/ AND test/
pnpm test                               # vitest run (all test/*.spec.ts, ~1s, no network/keys needed)
pnpm test test/search.spec.ts           # single file (args forward to vitest, no -- needed)
pnpm test test/search.spec.ts -t "bm25" # single test by name (pair with file path to keep it fast)
pnpm lint                               # eslint . — minimal config (unused-vars only); passing means little
pnpm build                              # tsc -p tsconfig.build.json && pnpm build:web (Vite → dist/web) && chmod
pnpm dev                                # tsx src/bin.ts (stdio)
pnpm dev --http                         # HTTP transport; also --port, --host, --sandbox, --insecure

In pnpm build, the || true guards only the chmod — a tsc failure DOES fail the build. pnpm typecheck remains the broader gate (it also covers test/**, which the build config excludes).
CI (.github/workflows/ci.yml) runs typecheck, lint, build, test in that order (build first: the Postgres-gated account frontend test serves dist/web and skips without it) on Node 20 and 22, plus a Docker build. All four must pass; the PR template also requires them as checkboxes.
A green pnpm test on a machine with NO sandbox runner does not prove the sandbox works: sandbox-execution tests are gated on await runner.available() and report a skip when their runner is unavailable. CI installs isolated-vm AND Deno, so both runners' gated tests execute there.

Read the full file on GitHub · 99 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +54 tokens per session 7c3c9d641f88
1mo ago Changed · +26 tokens per session c1797e8384f1
1mo ago Changed · +84 tokens per session 7f575e247ce7
2mo ago First seen · 99 lines · 3,564 tokens per session scan A acc4b46225bd

Subscribe to this mod's changes

fedreg-mcp-server CLAUDE.md is an instructions file published in the GitHub repository blen-labs/fedreg-mcp-server (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,728 tokens to every session, about $0.0149 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Legal and compliance

fedreg-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fedreg-mcp-server CLAUDE.mdblen-labs/fedreg-mcp-server	Instructions file	3	yesterday	Apache-2.0	A	3,728	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	today	MIT	A	4,335	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

fedreg-mcp-server: Instructions file for Claude Code