What is mcp-server-datahub CLAUDE.md?

Project instructions for a DataHub MCP server, a service that lets coding agents search metadata, follow data lineage, and list SQL queries. They cover setup, commands, testing, architecture, and authentication.

Use them when developing, testing, linting, or running the DataHub server and its FastMCP development environment.

They tell an agent how this repository works and how to run its checks without guessing about its tools or live DataHub requirements.

How acryldata/mcp-server-datahub configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to acryldata/mcp-server-datahub. 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/acryldata/mcp-server-datahub/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/acryldata/mcp-server-datahub

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/acryldata/mcp-server-datahub/claude-md/github.svg)](https://agentmods.dev/instructions/acryldata/mcp-server-datahub/claude-md)

Your own site

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

Per session 668 This file is loaded in full into every session.

When invoked 668 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	$0.00668	$0.00668
Opus 5.5	$0.00267	$0.00267
Sonnet 5.5	$0.00134	$0.00134
Haiku 4.5	$0.00067	$0.00067

Measured 21d ago against content hash 966a2cc9f8b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server-datahub 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 21d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mcp-server-datahub CLAUDE.md — 92% identical, 14 lines differ

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 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 Model Context Protocol (MCP) server implementation for DataHub. The server provides tools for searching entities, fetching metadata, traversing lineage graphs, and listing SQL queries. It's built using the FastMCP framework and integrates with DataHub's GraphQL API.

Development Commands

See DEVELOPING.md and Makefile for more details.

A quick summary is below:

make setup - Set up development environment (requires uv)
make lint - Run ruff formatting, linting and type checking
make test - Run pytest tests (most run offline; only the integration tests need a live DataHub instance)
make clean - Clean up build artifacts

Testing

Run all tests: make test
Single test file: uv run pytest tests/test_mcp/test_search_documents.py
Most tests run offline against mocked GraphQL responses — no DataHub instance needed.
The integration tests in tests/test_mcp_integration.py require a live DataHub instance with authentication (DATAHUB_GMS_URL / DATAHUB_GMS_TOKEN, or ~/.datahubenv). They skip automatically when no credentials are available.

Development Setup

Run the server using MCP inspector for development:

uv run fastmcp dev src/mcp_server_datahub/__main__.py --with-editable .

Note: Use fastmcp dev (not mcp dev), since this project uses the standalone FastMCP package.

Architecture

Core Components

mcp_server.py: Main server implementation with MCP tools
- get_entity(): Fetch entity metadata by URN
- search(): Search across DataHub entities with filters
- get_dataset_queries(): Get SQL queries for datasets
- get_lineage(): Traverse upstream/downstream lineage
GraphQL Integration: Uses GraphQL fragments for efficient queries
- gql/search.gql: Search queries
- gql/entity_details.gql: Entity metadata queries
- gql/queries.gql: SQL query retrieval

Read the full file on GitHub · 77 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.

21d ago Changed · +3 lines · +76 tokens per session 966a2cc9f8b3
2mo ago First seen · 74 lines · 592 tokens per session scan A 178bd41eaa54

Subscribe to this mod's changes

mcp-server-datahub CLAUDE.md is an instructions file published in the GitHub repository acryldata/mcp-server-datahub (85 stars, last pushed yesterday), licensed Apache-2.0. It adds 668 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 2026-08-30.

mcp-server-datahub CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server-datahub CLAUDE.mdacryldata/mcp-server-datahub	Instructions file	85	yesterday	Apache-2.0	A	668	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

mcp-server-datahub: Instructions file for Claude Code