What is mcp-docs CLAUDE.md?

Project instructions for mcp-docs, a server that gives AI assistants access to Markdown documentation through tools and resources. Its identity and documentation folder are configured through a TOML file and an environment variable.

Use them when developing or operating the mcp-docs project, including local runs, SSE or HTTP connections, MCP Inspector checks, and container builds.

They explain how to run, configure, inspect, and containerize the server. This avoids guessing the correct transport mode, port, or documentation location.

How gmantovani2005/mcp-docs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gmantovani2005/mcp-docs. 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/gmantovani2005/mcp-docs/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gmantovani2005/mcp-docs

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/gmantovani2005/mcp-docs/claude-md/github.svg)](https://agentmods.dev/instructions/gmantovani2005/mcp-docs/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gmantovani2005/mcp-docs/claude-md"><img src="https://agentmods.dev/badge/instructions/gmantovani2005/mcp-docs/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/gmantovani2005/mcp-docs/claude-md"><img src="https://agentmods.dev/badge/instructions/gmantovani2005/mcp-docs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,153 This file is loaded in full into every session.

When invoked 1,153 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	$0.01153	$0.01153
Opus 5.5	$0.00461	$0.00461
Sonnet 5.5	$0.00231	$0.00231
Haiku 4.5	$0.00115	$0.00115

Measured 2mo ago against content hash a2d0a29ce239, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-docs 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 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

Generic MCP server that exposes Markdown documentation to LLMs via tools and resources. Project identity (name, instructions, category labels) is configured via config.toml inside the docs directory. The docs directory path is set via the MCP_DOCS_DIR environment variable (defaults to ./docs).

Commands

uv sync                                      # install dependencies
uv run main.py                               # run server (stdio, default)
uv run main.py --transport sse               # SSE mode (default port 6060)
uv run main.py --transport streamable-http   # Streamable HTTP mode (/mcp endpoint)
uv run main.py --transport sse --host 0.0.0.0 --port 8080  # custom host/port
uv run mcp dev main.py                       # open MCP Inspector in browser

No test suite or linter is configured. The container transport is always streamable-http on port 8080.

Containers

# Build
docker build -f .containers/Dockerfile -t mcp-docs:latest .
podman build -f .containers/Dockerfile -t mcp-docs:latest .

# Run locally (requires docs/ directory)
docker compose up
podman compose up

# Kubernetes deploy
kubectl apply -f .containers/deployment.yaml
kubectl apply -f .containers/service.yaml

.containers/Dockerfile — imagem de produção; usa streamable-http na porta 8080
.containers/deployment.yaml — Kubernetes Deployment; edite image: antes de usar
.containers/service.yaml — Kubernetes Service (ClusterIP, porta 8080)
docker-compose.yaml — execução local; monta ./docs como volume somente-leitura em /docs
.dockerignore — exclui .venv/, docs/, .git/, .env do contexto de build Config (<docs-dir>/config.toml) is read once at startup — restart the server to pick up changes. MCP_DOCS_DIR overrides the default ./docs path and is loaded from .env via python-dotenv.

Read the full file on GitHub · 90 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 · 90 lines · 1,153 tokens per session scan A a2d0a29ce239

Subscribe to this mod's changes

mcp-docs CLAUDE.md is an instructions file published in the GitHub repository gmantovani2005/mcp-docs (0 stars, last pushed 6mo ago), licensed MIT. It adds 1,153 tokens to every session, about $0.0046 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.

mcp-docs CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-docs CLAUDE.mdgmantovani2005/mcp-docs	Instructions file	0	6mo ago	MIT	A	1,153	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

mcp-docs: Instructions file for Claude Code