ra-mcp: Instructions file for Claude Code

CLAUDE.md

ra-mcp CLAUDE.md is an instructions file for Claude Code from AI-Riksarkivet/ra-mcp. It costs 10,340 tokens per session, scanned A, original, Apache-2.0.

Project instructions for an MCP server that lets coding agents search transcribed historical documents from Sweden’s National Archives. The project is split into many shared Python packages.

In plain words
What is it for?
Use them when developing the archive search server, its document datasets, shared search libraries, or server utilities.
Why use it?
They explain the package layout and shared search and server components, so changes can fit the existing structure instead of duplicating code.

Instructions file for Claude Code

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

This is AI-Riksarkivet/ra-mcp's own configuration. It tells Claude Code how to work on ra-mcp 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 ra-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AI-Riksarkivet/ra-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/AI-Riksarkivet/ra-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AI-Riksarkivet/ra-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.

agentmods badge for ra-mcp CLAUDE.md

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

agentmods 80×15 button for ra-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ai-riksarkivet/ra-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-riksarkivet/ra-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,340 This file is loaded in full into every session.
When invoked 10,340 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.10340 $0.10340
Opus 5 $0.05170 $0.05170
Sonnet 5 $0.02068 $0.02068
Haiku 4.5 $0.01034 $0.01034

Measured 9d ago against content hash 39e996cc1bd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ra-mcp CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:7860/health
CLAUDE.md · 977 lines

How it starts

The opening of the file, as written. The whole thing — 977 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

ra-mcp (Riksarkivet Model Context Protocol) is an MCP server that provides access to transcribed historical documents from the Swedish National Archives (Riksarkivet).

Architecture

The project is organized as a uv workspace with 45 packages under packages/ plus a root server. This includes ra-mcp-dataset-lib (module ra_mcp_dataset_lib) — the shared LanceDB "spine" (one SearchResult; get_lancedb cached/thread-safe connections; build_fts_index + build_scalar_indexes; an instrumented lancedb_fts_search; SQL predicate builders; and the shared MCP-handler scaffold require_keyword + format_results) that the 13 dataset libraries and the pdf-mcp guide search all reuse instead of each rolling their own search. Cross-cutting MCP helpers live in ra-mcp-common: run_dev_server (the standalone dev entrypoint), mark_span_error + record_span_exception (telemetry), and the HTTPClient. Packages are grouped by role into subfolders:

  • packages/libs/ — domain libraries (*-lib), plus common
  • packages/mcps/ — FastMCP servers (*-mcp) that wrap a domain library as MCP tools/resources
  • packages/cli/ — CLI (search-cli, browse-cli) and terminal-UI (tui) front-ends
ra-mcp/
├── src/ra_mcp_server/          # Root: Server composition and main CLI
│   ├── server.py               # FastMCP composition entry point + AVAILABLE_MODULES registry
│   └── cli/app.py              # Typer CLI root (ra command)
├── packages/
│   ├── libs/                   # domain libraries (*-lib) + common
│   │   ├── common/             # ra-mcp-common: Shared HTTP client, formatting, datasets, telemetry
│   │   ├── xml-lib/            # ra-mcp-xml: ALTOClient (ALTO XML parsing)
│   │   ├── iiif-lib/           # ra-mcp-iiif-lib: IIIFClient
│   │   ├── oai-pmh-lib/        # ra-mcp-oai-pmh-lib: OAIPMHClient
│   │   ├── search-lib/         # ra-mcp-search-lib: Search domain (models, client, operations)
│   │   ├── browse-lib/         # ra-mcp-browse-lib: Browse domain (models, operations, url_generator)
│   │   └── <dataset>-lib/      # 14 dataset libs (diplomatics, sbl, sjomanshus, filmcensur,
│   │                           #   rosenberg, court, aktiebolag, faltjagare, suffrage,
│   │                           #   specialsok, dds, wincars, sj, tora)
│   ├── mcps/                   # FastMCP servers wrapping the libs (*-mcp)
│   │   ├── search-mcp/         # ra-mcp-search-mcp: MCP tools for search
│   │   ├── browse-mcp/         # ra-mcp-browse-mcp: MCP tool for browse
│   │   ├── guide-mcp/          # ra-mcp-guide-mcp: MCP resources for historical guides
│   │   ├── htr-mcp/            # ra-mcp-htr-mcp: Handwritten text recognition (HTRflow)
│   │   ├── viewer-mcp/         # ra-mcp-viewer-mcp: Interactive document viewer (MCP App UI)
│   │   ├── pdf-mcp/            # ra-mcp-pdf-mcp: Interactive PDF viewer (MCP App UI)
│   │   ├── label-mcp/          # ra-mcp-label-mcp: Label Studio import (optional)
│   │   └── <dataset>-mcp/      # 14 dataset MCP servers (one per dataset lib above)
│   └── cli/                    # CLI + TUI front-ends
│       ├── search-cli/         # ra-mcp-search-cli: CLI command for search
│       ├── browse-cli/         # ra-mcp-browse-cli: CLI command for browse
│       └── tui/                # ra-mcp-tui: Interactive terminal browser
├── resources/                  # Historical guide markdown files
├── pyproject.toml              # Workspace configuration
└── uv.lock                     # Shared lockfile

Read the full file on GitHub · 977 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. 9d ago First seen · 977 lines · 10,340 tokens per session scan A 39e996cc1bd2

Subscribe to this mod's changes

ra-mcp CLAUDE.md is an instructions file published in the GitHub repository AI-Riksarkivet/ra-mcp (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10,340 tokens to every session, about $0.0517 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens