What is french-politics-mcp CLAUDE.md?

Project instructions for Civis, an MCP server that retrieves exact, sourced passages from the 2022 French presidential manifestos of five parties.

Working on the server, its French-language search, Cloudflare Worker code, SQLite database, MCP tools, and manifesto data handling.

They give coding agents the project’s rules, structure, technology choices, and commands, while stressing that missing information must not be guessed or paraphrased.

How mael-app/french-politics-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mael-app/french-politics-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/mael-app/french-politics-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mael-app/french-politics-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/mael-app/french-politics-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mael-app/french-politics-mcp/claude-md)

Your own site

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

Per session 1,352 This file is loaded in full into every session.

When invoked 1,352 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	$0.01352	$0.01352
Opus 5.5	$0.00541	$0.00541
Sonnet 5.5	$0.00270	$0.00270
Haiku 4.5	$0.00135	$0.00135

Measured 2mo ago against content hash ebbe606bb414, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

french-politics-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 · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Civis — french-politics-mcp

Remote MCP server exposing the official manifestos of the 2022 French presidential election for five parties (LFI, RN, Renaissance, PS, LR). It retrieves exact passages with their source and never paraphrases: the client LLM writes the synthesis, the server only supplies verifiable quotes.

Core rule

The server must prefer saying nothing over implying a source it does not have. Every behaviour follows from this: a query with no match returns zero results and an explicit notFound, compare_parties reports not_found per party rather than inferring a stance, and quotes are byte-identical to the source document.

Stack

Cloudflare Workers, TypeScript, D1 (SQLite) with FTS5. Stateless: no Durable Object, Streamable HTTP on /mcp only. The Worker bundles no data; the corpus lives in D1.

A fresh McpServer instance is created per request (required since SDK 1.26).

Layout

src/index.ts        fetch handler, health check, createMcpHandler
src/server/         MCP surface: tools, resources, prompts
src/domain/         types, party metadata, topic taxonomy
src/search/         French language pipeline, FTS5 query builder
src/storage/        D1 access: search, passages, aggregates
ingest/             local pipeline: fetch, extract, normalize, build-sql
data/corpus/        corpus.json, the normalized artefact (generated, gitignored)
data/sql/           schema.sql (handwritten), seed.sql (generated, gitignored)
data/text/          extracted text, committed as consultable evidence
data/raw/           downloaded sources, gitignored except checksums.json

Commands

npm install              # installs git hooks and generates worker-configuration.d.ts
npm run dev              # wrangler dev on :8787
npm run typecheck
npm run ingest           # fetch, extract, normalize, build-sql
npm run corpus:check     # verify corpus invariants
npm run smoke            # drive a real MCP session against a running server
npm run stem:check       # verify stemmer convergence
npm run db:reset:local   # apply schema + seed to local SQLite

Read the full file on GitHub · 124 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 · 124 lines · 1,352 tokens per session scan A ebbe606bb414

Subscribe to this mod's changes

french-politics-mcp CLAUDE.md is an instructions file published in the GitHub repository mael-app/french-politics-mcp (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,352 tokens to every session, about $0.0054 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.

Backend and APIs Research french politics

french-politics-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
french-politics-mcp CLAUDE.mdmael-app/french-politics-mcp	Instructions file	0	5d ago	Apache-2.0	A	1,352	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

french-politics-mcp: Instructions file for Claude Code