Borrowing it
Nothing to install: this file belongs to watsona4/mcp-document-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/watsona4/mcp-document-server/master/CLAUDE.mdgit clone --depth 1 https://github.com/watsona4/mcp-document-serverWrote 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.
[](https://agentmods.dev/instructions/watsona4/mcp-document-server/claude-md)<a href="https://agentmods.dev/instructions/watsona4/mcp-document-server/claude-md"><img src="https://agentmods.dev/badge/instructions/watsona4/mcp-document-server/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.
<a href="https://agentmods.dev/instructions/watsona4/mcp-document-server/claude-md"><img src="https://agentmods.dev/badge/instructions/watsona4/mcp-document-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00727 | $0.00727 |
| Opus 5.5 | $0.00291 | $0.00291 |
| Sonnet 5.5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
mcp-document-server 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8000/health # Health check 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
MCP Document Server - A Python FastAPI-based Model Context Protocol (MCP) server that provides Claude AI with secure, read-only access to local documents. Supports both network (SSE/HTTP) and local (STDIO) transports.
Commands
Docker (Recommended)
docker-compose up -d # Start server
docker-compose down # Stop server
docker-compose logs -f # View logs
docker-compose up -d --build # Rebuild and start
Direct Python
python -m venv venv
venv\Scripts\activate # Windows
source venv/bin/activate # Linux/Mac
pip install -r requirements.txt
python server.py # Run server
Testing
curl http://localhost:8000/health # Health check
python test_server.py # Run test client
Architecture
Claude AI
│
├── STDIO (local) ──┐
│ │
└── SSE/HTTP ───────┴──→ MCP Document Server (FastMCP + FastAPI)
│
├── list_documents() - List files with metadata
├── read_document() - Read with format parsing
├── search_documents() - Full-text search
└── documents://list - Resource endpoint
│
↓
Documents Directory (read-only)
Core Components
server.py - Main implementation:
is_safe_path()- Path traversal protection (validates all paths stay within DOCUMENTS_PATH)get_file_info()- File metadata extractionlist_documents()/read_document()/search_documents()- MCP toolsmain()- Entry point with transport selection (SSE vs STDIO)
test_server.py - Async test client that validates all MCP tools via Docker exec
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 · 727 tokens per session scan A 77189d6b38b4
mcp-document-server CLAUDE.md is an instructions file published in the GitHub repository watsona4/mcp-document-server (0 stars, last pushed 9mo ago), licensed MIT. It adds 727 tokens to every session, about $0.0029 per session on Opus 5.5. 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 2026-08-31.
mcp-document-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-document-server CLAUDE.mdwatsona4/mcp-document-server | Instructions file | 0 | 9mo ago | MIT | A | 727 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |