What is fda-mcp CLAUDE.md?

A repository instruction file for Claude Code, documenting an FDA data server, its layout, architecture, development commands, and tests. The server uses the OpenFDA API, a public service for searching U.S. Food and Drug Administration data.

It helps Claude Code install dependencies, start the server, run unit or integration tests, and locate the main source files.

It gives the coding agent the project-specific context needed to run the right commands and follow the existing structure.

How Limecooler/fda-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Limecooler/fda-mcp. 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/Limecooler/fda-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Limecooler/fda-mcp

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/limecooler/fda-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/limecooler/fda-mcp/claude-md)

Your own site

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

Per session 641 This file is loaded in full into every session.

When invoked 641 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	$0.00641	$0.00641
Opus 5.5	$0.00256	$0.00256
Sonnet 5.5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash 3f8fc2d4b214, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fda-mcp 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 2mo ago.

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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 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.

Project Overview

FDA MCP — an MCP server providing access to FDA data via the OpenFDA API. Wraps all 21 OpenFDA endpoints plus FDA decision document retrieval into 12 MCP tools optimized for LLM consumption.

Development Commands

Install dependencies: uv sync --all-extras
Run server: uv run fda-mcp
Run unit tests: uv run pytest
Run integration tests (hits real FDA API): uv run pytest -m integration
Run specific test file: uv run pytest tests/test_endpoints.py -v

Architecture

Language: Python 3.11+, async throughout
MCP SDK: mcp with FastMCP decorator API
HTTP Client: httpx (async)
PDF Extraction: pdfplumber + pytesseract/pdf2image OCR fallback
Transport: stdio (standard for Claude Desktop / Claude Code)

Source Layout

src/fda_mcp/
├── server.py          -- FastMCP server entry point
├── config.py          -- Environment-based configuration
├── errors.py          -- Custom error types
├── openfda/           -- OpenFDA API client layer
│   ├── endpoints.py   -- Enum of all 21 endpoints
│   ├── client.py      -- Async HTTP client with rate limiting
│   └── summarizer.py  -- Response summarization per endpoint
├── documents/         -- FDA decision document retrieval
│   ├── urls.py        -- URL pattern construction
│   └── fetcher.py     -- PDF download + text extraction
├── tools/             -- 12 MCP tool handlers
│   ├── search.py      -- 9 search tools
│   ├── count.py       -- count_records tool
│   ├── fields.py      -- list_searchable_fields tool
│   └── decision_documents.py
└── resources/         -- 3 MCP resources
    ├── query_syntax.py
    ├── endpoints_resource.py
    └── field_definitions.py

Configuration

OPENFDA_API_KEY — optional API key for higher rate limits (240 req/min vs 40)
OPENFDA_TIMEOUT — request timeout in seconds (default: 30)
OPENFDA_MAX_CONCURRENT — max concurrent API requests (default: 4)
FDA_PDF_TIMEOUT — PDF download timeout in seconds (default: 60)
FDA_PDF_MAX_LENGTH — default max text chars from PDFs (default: 8000)

Read the full file on GitHub · 63 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.

2mo ago First seen · 63 lines · 641 tokens per session scan A 3f8fc2d4b214

Subscribe to this mod's changes

fda-mcp CLAUDE.md is an instructions file published in the GitHub repository Limecooler/fda-mcp (1 stars, last pushed 8mo ago), licensed MIT. It adds 641 tokens to every session, about $0.0026 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.

fda-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fda-mcp CLAUDE.mdLimecooler/fda-mcp	Instructions file	1	8mo ago	MIT	A	641	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

fda-mcp: Instructions file for Claude Code