What is loc-mcp CLAUDE.md?

Instructions and tools for a local server that searches the U.S. Library of Congress online collections, including newspapers, books, and manuscripts.

Searching collections by words, dates, language, state, title, format, contributor, or subject; retrieving matching snippets, citation links, and OCR text.

It avoids having to build Library of Congress API requests, page-level searches, text downloads, and result handling from scratch.

How nestordemeure/loc-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nestordemeure/loc-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/nestordemeure/loc-mcp/main/CLAUDE.md

Clone the repo

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

Your own site

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

Per session 2,574 This file is loaded in full into every session.

When invoked 2,574 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	$0.02574	$0.02574
Opus 5.5	$0.01030	$0.01030
Sonnet 5.5	$0.00515	$0.00515
Haiku 4.5	$0.00257	$0.00257

Measured 2mo ago against content hash 40e02f00d3ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loc-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 · 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.

Library of Congress MCP Server

A CLI and an MCP server for the JSON API of the Library of Congress: newspapers, books and manuscripts. Each item has a full-text index, and each item resolves to the individual page.

Stack

Python ≥3.12, uv, fastMCP ≥2.0.0, httpx ≥0.27.0

Functions

A full-text search at page level across all of loc.gov, or limited to one collection
Filters for the date range, the language, the US state, the title, the material format, the contributor and the subject heading
Keyword-in-context snippets for any page-level reference, with citation URLs
An OCR text download with a local cache, for one page or for a full item
Pagination at up to 150 results for each request

Structure

loc-mcp/
├── .claude/skills/loc-search/   # Skill documenting the CLI
├── src/loc_mcp/
│   ├── __init__.py
│   ├── client.py           # API client + caching
│   ├── cli.py              # `locgov` command-line interface
│   ├── paths.py            # Cache location resolution
│   ├── ratelimit.py        # Cross-process request pacing
│   ├── server.py           # FastMCP tools
│   └── install.py          # MCP server installer
├── pyproject.toml
└── CLAUDE.md               # This file

client.py holds all the behaviour. server.py and cli.py are thin presentation layers over it, so the search semantics and the cache stay identical for each method of access. The CLI shows each filter without a condition. The MCP server hides them behind --enable-advanced-search.

API Details

The dedicated chroniclingamerica.loc.gov API does not exist now. You can reach Chronicling America only as a collection of loc.gov. Thus this client uses the general API, and it treats that collection as one --collection value and not as a special case. The default scope is the full site.

Three services, all without a key and without authentication:

Service	URL	Returns
Search	`https://www.loc.gov/collections/<slug>/?fo=json` or `/search/?fo=json`	JSON
Resource metadata	the same host with `at=resources`	JSON
Snippets and OCR	`https://tile.loc.gov/text-services/word-coordinates-service`	JSON

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.

2mo ago First seen · 103 lines · 2,574 tokens per session scan A 40e02f00d3ee

Subscribe to this mod's changes

loc-mcp CLAUDE.md is an instructions file published in the GitHub repository nestordemeure/loc-mcp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,574 tokens to every session, about $0.0103 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.

Research library-of-congress mcp-server skills

loc-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
loc-mcp CLAUDE.mdnestordemeure/loc-mcp	Instructions file	0	3mo ago	Apache-2.0	A	2,574	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

loc-mcp: Instructions file for Claude Code