What is fbi-crime-data-mcp CLAUDE.md?

A set of Claude Code instructions for an FBI Crime Data MCP server, a Python service that provides tools for querying the FBI Crime Data Explorer API. It documents setup, running, tests, architecture, caching, and response handling.

It is for installing dependencies, starting the server, running tests, understanding its 17 tools, and finding key server and middleware components.

It gives a coding agent the project context needed to work consistently in the repository.

How dathere/fbi-crime-data-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dathere/fbi-crime-data-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/dathere/fbi-crime-data-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dathere/fbi-crime-data-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/dathere/fbi-crime-data-mcp/claude-md.svg)](https://agentmods.dev/instructions/dathere/fbi-crime-data-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dathere/fbi-crime-data-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dathere/fbi-crime-data-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 934 This file is loaded in full into every session.

When invoked 934 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	$0.00934	$0.00934
Opus 5	$0.00467	$0.00467
Sonnet 5	$0.00187	$0.00187
Haiku 4.5	$0.00093	$0.00093

Measured 6d ago against content hash f7732e35c478, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fbi-crime-data-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 6d 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 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

FBI Crime Data MCP Server — a Python MCP server providing 17 tools (15 for querying the FBI Crime Data Explorer API at https://api.usa.gov/crime/fbi/cde, plus 2 admin tools for cache and spillover management). Built with fastmcp (v3.2+) and httpx, deployable via uvx fbi-crime-data-mcp.

Build & Run

uv sync                                           # install deps
FBI_API_KEY=xxx uv run fbi-crime-data-mcp          # run server (stdio)
uv run pytest                                      # run tests
FBI_API_KEY=xxx uv run pytest -m integration        # integration tests (hits real API)

Architecture

src/fbi_crime_data_mcp/server.py — FastMCP server entry point with lifespan context. Imports all tool modules. Configures three ResponseCachingMiddleware instances with FileTreeStore for tiered disk-backed caching (90-day TTL for summaries/trends/reference/NIBRS estimation; 30-day TTL for agency lookups and granular crime/officer data; 1-day TTL for homepage summary), plus a ResponseSpilloverMiddleware for oversized responses. Cache persists to ~/.cache/fbi-crime-data-mcp/.
src/fbi_crime_data_mcp/api_client.py — Shared httpx.AsyncClient wrapper with sliding-window rate limiter (1000 req/hr). AppContext dataclass is the lifespan context available to all tools via ctx.lifespan_context.
src/fbi_crime_data_mcp/response_utils.py — Post-processing for API responses: process_crime_response() trims verbose sections (tooltips, participated_population) and aggregates monthly mm-yyyy data into yearly totals; filter_agencies_by_name() does case-insensitive substring filtering on agency lists.
src/fbi_crime_data_mcp/constants.py — All validation enums: SRS offenses, NIBRS codes, arrest offenses, bias codes, LESDC chart types, states.
src/fbi_crime_data_mcp/spillover.py — ResponseSpilloverMiddleware saves oversized tool responses (>128K chars) to disk under ~/.cache/fbi-crime-data-mcp/spillover/, returning a preview with the file path. Content-addressed filenames avoid duplicates.
src/fbi_crime_data_mcp/validators.py — Shared validation helpers used by tools: level, data_type, aggregate, state, ORI, date format (mm-yyyy / yyyy), year range, and offense code validators. Also provides build_geo_path() for constructing national/state/agency API paths and effective_aggregate() for aggregate passthrough logic.
src/fbi_crime_data_mcp/tools/ — One module per tool, each registers via @mcp.tool() decorator on the shared mcp instance imported from server.py.

Read the full file on GitHub · 36 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.

6d ago First seen · 36 lines · 934 tokens per session scan A f7732e35c478

Subscribe to this mod's changes

fbi-crime-data-mcp CLAUDE.md is an instructions file published in the GitHub repository dathere/fbi-crime-data-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 934 tokens to every session, about $0.0047 per session on Opus 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.

Research crime fbi mcp opendata

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

fbi-crime-data-mcp: Instructions file for Claude Code