dataproduct-mcp CLAUDE.md

dataproduct-mcp CLAUDE.md is an instructions file for coding agents from entropy-data/dataproduct-mcp. It costs 1,237 tokens per session, scanned A, original, MIT.

A project guide for Claude Code, an AI coding assistant, when working on the dataproduct-mcp repository. It describes the project, setup commands, tests, server startup, and main components.

In plain words
What is it for?
Use it to guide development, testing, debugging, and setup of the dataproduct-mcp project.
Why use it?
It gives the coding assistant the repository-specific context and commands needed to work consistently. It reduces guesswork about how to install dependencies, test changes, and run the server.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/entropy-data/dataproduct-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/entropy-data/dataproduct-mcp

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 dataproduct-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/entropy-data/dataproduct-mcp/claude-md.svg)](https://agentmods.dev/instructions/entropy-data/dataproduct-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/entropy-data/dataproduct-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/entropy-data/dataproduct-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,237 This file is loaded in full into every session.
When invoked 1,237 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01237 $0.01237
Opus 5 $0.00619 $0.00619
Sonnet 5 $0.00247 $0.00247
Haiku 4.5 $0.00124 $0.00124

Measured 3d ago against content hash ec067a2626c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dataproduct-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 3d 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 · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 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

This is a Data Product MCP server that enables AI agents to discover and access data products through the Data Mesh Manager platform. It acts as a bridge between AI systems and data governance infrastructure, allowing agents to find relevant data products, check access permissions, and understand data contracts.

Key Commands

Development Setup

# Install dependencies with dev tools
uv sync --extra dev
uv pip install -e .

Testing

# Run all tests (uses pytest with async support)
uv run pytest

Running the Server

# Start MCP server (uses stdio transport)
uv run python -m dataproduct_mcp.server

# Use with MCP Inspector for debugging
npx @modelcontextprotocol/inspector --config config.json --server dataproduct

Architecture

Core Components

MCP Server (server.py)

  • Built with FastMCP framework
  • Exposes tools for data product discovery
  • Uses stdio transport for MCP communication
  • Implements async tools with proper error handling

API Client Layer (datameshmanager/)

  • datamesh_manager_client.py: Async HTTP client using httpx
  • models.py: Pydantic models for API response validation
  • Handles authentication via DATAMESH_MANAGER_API_KEY environment variable

MCP Tools Architecture

The server exposes these tools to AI agents:

  1. dataproduct_list - List/filter data products by search terms, archetype, status
  2. dataproduct_search - Semantic search for data products
  3. dataproduct_get - Retrieve detailed data product info including access status
  4. datacontract_get - Get YAML data contract specifications

Data Flow

  1. Discovery: AI agents use list/search tools to find relevant data products
  2. Governance: Check access status and permissions via get tools
  3. Integration: Use returned server information to connect to actual data sources

Read the full file on GitHub · 143 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. 3d ago First seen · 143 lines · 1,237 tokens per session scan A ec067a2626c1

Subscribe to this mod's changes

dataproduct-mcp CLAUDE.md is an instructions file published in the GitHub repository entropy-data/dataproduct-mcp (46 stars, last pushed 10mo ago), licensed MIT. It adds 1,237 tokens to every session, about $0.0062 per session on Opus 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 2026-08-30.