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.
npx agentmods add instructions/txn2/mcp-datahub/claude-mdgit clone --depth 1 https://github.com/txn2/mcp-datahubWrote 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/txn2/mcp-datahub/claude-md)<a href="https://agentmods.dev/instructions/txn2/mcp-datahub/claude-md"><img src="https://agentmods.dev/badge/instructions/txn2/mcp-datahub/claude-md.svg" alt="Measured on agentmods" 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 | $0.03327 | $0.03327 |
| Opus 5 | $0.01664 | $0.01664 |
| Sonnet 5 | $0.00665 | $0.00665 |
| Haiku 4.5 | $0.00333 | $0.00333 |
Grade A, and why
mcp-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 325 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 when working with this project.
Project Overview
mcp-datahub is a composable Go library for building custom MCP (Model Context Protocol) servers that integrate DataHub metadata capabilities. It is part of the txn2 MCP toolkit ecosystem alongside mcp-trino.
Project Positioning
This is NOT a replacement for the official DataHub MCP server. This library serves a different purpose:
-
Primary Use: A composable building block for creating unified MCP servers that combine multiple data tools (DataHub + Trino + dbt + custom tools) into a single AI assistant interface.
-
Secondary Use: The included
mcp-datahubbinary is a reference implementation that demonstrates library capabilities—functional as a standalone DataHub MCP server.
Key Design Principles
- Composable: Designed to work alongside other MCP toolkits (mcp-trino, etc.)
- Library-first: The CLI binary is a reference implementation, not the primary deliverable
- Extensible: Middleware system for adding auth, audit logging, rate limiting
- Island architecture: No dependencies on other txn2 libraries
- Generic: No domain-specific logic; suitable for any DataHub deployment
Architecture
pkg/
├── client/ # DataHub GraphQL client (standalone, no MCP dependency)
├── multiserver/ # Multi-server configuration and connection management
├── types/ # Domain types (entities, schema, lineage, etc.)
├── tools/ # MCP toolkit (composable tool registration)
├── integration/ # Extension interfaces for custom integrations
└── extensions/ # Optional middleware: logging, metrics, error hints, config files
internal/
└── server/ # Reference implementation server setup
cmd/
└── mcp-datahub/ # Reference implementation CLI binary
mcpb/
├── manifest.json # MCPB bundle manifest for Claude Desktop
└── build.sh # Build script for .mcpb bundles
Composition Pattern
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.
- 5d ago First seen · 325 lines · 3,327 tokens per session scan A ec05b7c9c696
mcp-datahub CLAUDE.md is an instructions file published in the GitHub repository txn2/mcp-datahub (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,327 tokens to every session, about $0.0166 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 2026-08-31.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.