What is td-mcp-server CLAUDE.md?

Repository instructions for an MCP server that exposes Treasure Data features to AI assistants. MCP, or Model Context Protocol, is a standard way for assistants to call tools provided by another program.

Use them when building or testing the Treasure Data server, checking types and lint rules, formatting code, or running unit and integration tests.

They collect the project's development, testing, architecture, and code-quality rules in one place.

How treasure-data/td-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to treasure-data/td-mcp-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.

Copy the file

curl -O https://raw.githubusercontent.com/treasure-data/td-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/treasure-data/td-mcp-server

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/treasure-data/td-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/treasure-data/td-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/treasure-data/td-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/treasure-data/td-mcp-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.

Your own site · 80×15

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

Per session 1,496 This file is loaded in full into every session.

When invoked 1,496 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	$0.01496	$0.01496
Opus 5.5	$0.00598	$0.00598
Sonnet 5.5	$0.00299	$0.00299
Haiku 4.5	$0.00150	$0.00150

Measured 2mo ago against content hash a1f1d01b2563, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

td-mcp-server 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 · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 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.

Commands

Development

npm run dev - Run TypeScript directly with tsx (hot reload)
npm run build - Compile TypeScript to dist/
npm start - Run compiled code from dist/

Testing

npm test - Run all tests with Vitest
npm test tests/config.test.ts - Run specific test file
npm run test:watch - Run tests in watch mode
npm run test:coverage - Run tests with coverage report
npm run test:unit - Run only unit tests (excludes integration)
npm run test:integration - Run integration tests (requires TD_API_KEY_DEVELOPMENT_AWS)

Code Quality

npm run lint - Check ESLint rules
npm run format - Auto-format with Prettier
npm run typecheck - Type-check without building

Architecture Overview

This is an MCP (Model Context Protocol) server that exposes Treasure Data functionality to AI assistants. The architecture follows a security-first, modular design:

Core Components

MCP Server (src/index.ts) - Entry point that registers tools with the MCP SDK
Configuration (src/config.ts) - Validates and manages all server settings with environment variable support
Trino Client (src/client/) - Wraps trino-client for TD-specific authentication using X-Trino-User header
CDP Client (src/client/cdp/) - HTTP client for TD Customer Data Platform API using TD1 authentication
Workflow Client (src/client/workflow/) - HTTP client for Digdag workflow API using TD1 authentication
Security Layer (src/security/) - Validates SQL queries and maintains audit logs
MCP Tools (src/tools/) - Individual tool implementations for database operations
CDP Tools (src/tools/cdp/) - Tools for interacting with CDP segments and activations
Workflow Tools (src/tools/workflow/) - Tools for monitoring and controlling Digdag workflows

Key Design Patterns

Read-Only by Default: The query tool only allows SELECT/SHOW/DESCRIBE. Write operations require explicit enable_updates=true and use the separate execute tool.

Read the full file on GitHub · 115 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 · 115 lines · 1,496 tokens per session scan A a1f1d01b2563

Subscribe to this mod's changes

td-mcp-server CLAUDE.md is an instructions file published in the GitHub repository treasure-data/td-mcp-server (7 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,496 tokens to every session, about $0.0060 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.

td-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
td-mcp-server CLAUDE.mdtreasure-data/td-mcp-server	Instructions file	7	3d ago	Apache-2.0	A	1,496	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	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	today	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

td-mcp-server: Instructions file for Claude Code