fec-mcp-server: Instructions file for Claude Code

CLAUDE.md

fec-mcp-server CLAUDE.md is an instructions file for Claude Code from sh-patterson/fec-mcp-server. It costs 1,027 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that queries federal campaign-finance data through the OpenFEC API, a public US government data service.

In plain words
What is it for?
Use them when building, testing, type-checking, running, or extending tools that retrieve and classify FEC campaign-finance data.
Why use it?
They give contributors the commands, file structure, configuration needs, and testing approach required to work consistently on the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is sh-patterson/fec-mcp-server's own configuration. It tells Claude Code how to work on fec-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fec-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sh-patterson/fec-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/sh-patterson/fec-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sh-patterson/fec-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.

agentmods badge for fec-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sh-patterson/fec-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/sh-patterson/fec-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sh-patterson/fec-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sh-patterson/fec-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.

agentmods 80×15 button for fec-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sh-patterson/fec-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sh-patterson/fec-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,027 This file is loaded in full into every session.
When invoked 1,027 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01027 $0.01027
Opus 5.5 $0.00411 $0.00411
Sonnet 5.5 $0.00205 $0.00205
Haiku 4.5 $0.00103 $0.00103

Measured 2mo ago against content hash 2eff95cbb87d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fec-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 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 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

MCP (Model Context Protocol) server providing tools to query FEC campaign finance data via the OpenFEC API. Designed for non-partisan campaign finance transparency research.

Commands

npm run build               # Compile TypeScript to build/
npm run test                # Run tests once
npm run test:e2e            # Run e2e tests against live FEC API
npm run typecheck           # Type check without emitting
npm run dev                 # Run with tsx watch (development)
npm run acceptance:fec-day  # Live acceptance checks (federal targets)
npm run acceptance:notable  # Live smoke test (notable classification)

Run a single test file:

npx vitest run tests/tools/get-receipts.test.ts

Architecture

MCP Server Flow

src/index.ts          → Entry point, STDIO transport
src/server.ts         → McpServer creation
src/tools/index.ts    → Tool registration hub (registerTools function)
src/config.ts         → Loads FEC_API_KEY from environment

Tool Pattern

Each tool follows this structure:

  • src/tools/{tool-name}.ts - Tool definition constant + execute function
  • src/schemas/{tool-name}.schema.ts - Zod schema object for MCP SDK

Tools export:

  • {TOOL_NAME}_TOOL - Contains name, description, inputSchema
  • execute{ToolName} - Async function taking FECClient + params

API Layer

  • src/api/client.ts - FECClient class wrapping fetch calls to OpenFEC
  • src/api/endpoints.ts - API URL constants and endpoint builders
  • src/api/types.ts - FEC response interfaces (FECCandidate, FECScheduleA, etc.)

Notable Engine

src/notable/reference-data.ts  → Loads bundled reference lists (lobbyists, PACs, etc.)
src/notable/matchers.ts        → Fuzzy + exact matching against reference lists
src/notable/classifier.ts      → Classifies receipts/disbursements as notable with flag reasons
src/notable/formatters.ts      → Renders notable blocks for tool output
resources/reference-lists/     → Bundled CSV snapshots (lobbyists, leadership PACs, etc.)

Read the full file on GitHub · 103 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.

  1. 2mo ago First seen · 103 lines · 1,027 tokens per session scan A 2eff95cbb87d

Subscribe to this mod's changes

fec-mcp-server CLAUDE.md is an instructions file published in the GitHub repository sh-patterson/fec-mcp-server (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,027 tokens to every session, about $0.0041 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.

Related

fec-mcp-server CLAUDE.md compared with instructions from other repositories

fec-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fec-mcp-server CLAUDE.mdsh-patterson/fec-mcp-serverInstructions file41mo agoMITA1,027Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode