What is your-docs-mcp CLAUDE.md?

Project instructions for your-docs-mcp, a server that gives AI assistants structured access to documentation through the Model Context Protocol, a standard way for tools and assistants to communicate. It covers setup, architecture, testing, linting, type checking, and documentation validation.

Use it when developing your-docs-mcp, running its MCP or web server, validating documentation, or running tests, formatting, and type checks.

It gives contributors the project’s expected commands and conventions in one place. This reduces guesswork when changing, checking, or running the documentation server.

How esola-thomas/your-docs-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to esola-thomas/your-docs-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/esola-thomas/your-docs-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/esola-thomas/your-docs-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/esola-thomas/your-docs-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/esola-thomas/your-docs-mcp/claude-md)

Your own site

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

Per session 672 This file is loaded in full into every session.

When invoked 672 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	$0.00672	$0.00672
Opus 5.5	$0.00269	$0.00269
Sonnet 5.5	$0.00134	$0.00134
Haiku 4.5	$0.00067	$0.00067

Measured 2mo ago against content hash 2fc65defd9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

your-docs-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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

your-docs-mcp

Hierarchical Documentation MCP Server — gives AI assistants structured access to documentation via the Model Context Protocol.

Commands

Install: pip install -e ".[dev]" (dev) or pip install -e ".[dev,vector,pdf]" (all features)
Test: pytest (all) or pytest tests/unit/ tests/integration/ tests/contract/
Lint: ruff check . and ruff format .
Type check: mypy docs_mcp/
Run MCP server: your-docs-mcp (stdio, for AI clients)
Run web server: your-docs-server (HTTP on port 8123, with MCP SSE transport)
Validate docs: python scripts/validate_docs.py

Architecture

docs_mcp/
├── __main__.py          # CLI entry points (mcp_main, main)
├── core/
│   ├── config.py        # Pydantic settings (env vars, YAML config)
│   ├── models/          # Document, Category, SearchResult models
│   ├── services/        # Markdown parsing, hierarchy, search, cache
│   ├── security/        # Path validation, input sanitization
│   └── utils/           # Structured logging
├── mcp/
│   ├── server.py        # MCP server (stdio transport)
│   └── handlers/
│       ├── registry.py  # Shared MCP handler registration (tools + resources)
│       ├── tools.py     # MCP tool implementations (search, navigate, PDF)
│       └── resources.py # MCP resource handlers
├── web/
│   ├── app.py           # FastAPI web server + REST API + MCP SSE
│   ├── routes.py        # Server-rendered documentation pages
│   ├── partials.py      # HTMX partial endpoints
│   ├── templates/       # Jinja2 templates
│   └── static/          # CSS, JS, vendor assets
├── vector/              # ChromaDB semantic search (optional)
└── pdf/                 # PDF documentation generation

Conventions

Ruff: line-length 100, target py310, select E/F/I/N/W/UP, ignore E501
Type hints: required on all public interfaces
Async: use async/await for all I/O operations
Models: Pydantic v2 with strict typing
Logging: use docs_mcp.utils.logger for structured logging
Tests: pytest + pytest-asyncio, 80% min coverage (target 95%+)
TDD: write tests first, verify they fail, then implement (see constitution)

Read the full file on GitHub · 57 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 · 57 lines · 672 tokens per session scan A 2fc65defd9fd

Subscribe to this mod's changes

your-docs-mcp CLAUDE.md is an instructions file published in the GitHub repository esola-thomas/your-docs-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 672 tokens to every session, about $0.0027 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.

Building agents Documents

your-docs-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
your-docs-mcp CLAUDE.mdesola-thomas/your-docs-mcp	Instructions file	0	3mo ago	MIT	A	672	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

your-docs-mcp: Instructions file for Claude Code