What is civicgraph-mcp CLAUDE.md?

Project instructions for building an MCP server that connects federal donations, lobbying, and government-contract data into a graph. A knowledge graph represents entities such as people and organizations as connected nodes and records their relationships as links.

Use it when developing the civicgraph-mcp project: resolve entities across the FEC, Senate lobbying, and USASpending data, expose their connections, and document the project’s technical and data-source rules.

The difficult problem is matching the same person or organization across datasets with different formats without making unjustified merges. The instructions require evidence and confidence information for these links.

How cstillick/civicgraph-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cstillick/civicgraph-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/cstillick/civicgraph-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cstillick/civicgraph-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/cstillick/civicgraph-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/cstillick/civicgraph-mcp/claude-md)

Your own site

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

Per session 787 This file is loaded in full into every session.

When invoked 787 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	$0.00787	$0.00787
Opus 5	$0.00394	$0.00394
Sonnet 5	$0.00157	$0.00157
Haiku 4.5	$0.00079	$0.00079

Measured 8d ago against content hash 4d7a2288153d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

civicgraph-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 8d 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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — civicgraph-mcp

You are building an MCP server that exposes a linked money-in-politics graph across federal donations (FEC), lobbying (Senate LDA), and contracts (USASpending). Read SPEC.md and BUILD_PLAN.md. The product is the entity resolution + graph, not the raw data — the raw data is already wrapped by others. Build this only after the simpler repos; reuse their ingestion patterns.

What this project is

A knowledge-graph MCP. Nodes = people/orgs/committees/agencies. Edges = donated_to, lobbied_for, contracted_with, employed_by, etc. Tools let an agent resolve a name to an entity and walk its connections across all three domains.

Core principles

Entity resolution is the product. Matching "John A. Smith" across three datasets with different formats is the hard, valuable core. Make it explicit, scored, and explainable — never silently merge.
Explainable links only. Every merge and every edge exposes its evidence (matching features, source record, date). A confident-but-wrong link in accountability data is a serious failure. Prefer surfacing a possible match with a confidence score over an unexplained automatic merge.
Build on shoulders. The ingestion layer mirrors statefinance-mcp (snapshot raw → normalize → store). Don't reinvent it.
Federal scope, clearly bounded. v1 is FEC + LDA + USASpending. State data is a later bridge to statefinance-mcp.

Tech stack (default)

Python 3.11+, uv.
Official MCP SDK (mcp, FastMCP).
Graph store: start with DuckDB + explicit edge tables (portable, no server). Consider a graph DB (e.g., Kùzu/embedded) only if traversal needs outgrow SQL — document the decision, don't pre-optimize.
Entity resolution: rapidfuzz for string similarity, blocking keys (normalized name + state/zip + employer), deterministic + scored probabilistic matching. Keep a human-reviewable "match candidates" table.
httpx, pydantic v2, polars/pandas for ingestion.

Data sources (federal, free)

Read the full file on GitHub · 41 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.

8d ago First seen · 41 lines · 787 tokens per session scan A 4d7a2288153d

Subscribe to this mod's changes

civicgraph-mcp CLAUDE.md is an instructions file published in the GitHub repository cstillick/civicgraph-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 787 tokens to every session, about $0.0039 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.

Data and AI

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 · 5,153 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

civicgraph-mcp: Instructions file for Claude Code