What is kklab-mlit-dpf-mcp CLAUDE.md?

A set of Claude Code instructions for a project that provides access to Japanese government infrastructure data through a natural-language interface. The project is an unofficial wrapper around the MLIT Data Platform API; MLIT is Japan's Ministry of Land, Infrastructure, Transport and Tourism.

Use it when working on the project's MCP server, API client, data searches, data retrieval, code normalization, authentication, retries, rate limits, or caching.

It gives the coding agent the project's overview, architecture, main components, and rules for building GraphQL queries. This reduces the need to explain how the repository works before making changes.

How kkawailab/kklab-mlit-dpf-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kkawailab/kklab-mlit-dpf-mcp. 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/kkawailab/kklab-mlit-dpf-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kkawailab/kklab-mlit-dpf-mcp

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/kkawailab/kklab-mlit-dpf-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kkawailab/kklab-mlit-dpf-mcp/claude-md)

Your own site

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

Per session 1,811 This file is loaded in full into every session.

When invoked 1,811 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	$0.01811	$0.01811
Opus 5	$0.00905	$0.00905
Sonnet 5	$0.00362	$0.00362
Haiku 4.5	$0.00181	$0.00181

Measured 9d ago against content hash ada89d09365e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kklab-mlit-dpf-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 9d 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 · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 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 an unofficial MCP (Model Context Protocol) server that wraps the MLIT (Ministry of Land, Infrastructure, Transport and Tourism) Data Platform API. It enables LLMs to search and retrieve Japanese government infrastructure data through natural language queries.

Important: This is NOT an official MLIT project and has NO endorsement from the Japanese government.

Architecture

Core Components

MCP Server Layer (src/server.py)

Defines MCP tools using the mcp SDK
Each tool corresponds to an API operation (search, get_data, normalize_codes, etc.)
Tools validate inputs using Pydantic schemas and delegate to MLITClient
The server runs via stdio transport (stdio_server)

API Client Layer (src/client.py)

MLITClient: Async GraphQL client for MLIT Data Platform API
Handles authentication via API key header
Implements retry logic with exponential backoff for transient errors (429, 5xx)
Token-bucket rate limiter (default: 4 RPS)
Caches prefecture/municipality data to reduce API calls
Uses aiohttp for async HTTP operations

Schema Layer (src/schemas.py)

Pydantic models for input validation
Key schemas: SearchBase, SearchByRect, SearchByPoint, SearchByAttr, GetAllDataInput
Validators ensure constraints (e.g., size capped at 500)

Configuration (src/config.py)

Loads .env file via python-dotenv
Required: MLIT_API_KEY
Optional: MLIT_BASE_URL (defaults to https://www.mlit-data.jp/api/v1/)
Settings validation via Pydantic

Utilities (src/utils.py)

JSON logger with structured logging
RateLimiter: Token-bucket async rate limiter
Timer: Context manager for performance tracking
Request ID generation for tracing

GraphQL Query Building

The client builds GraphQL queries dynamically based on tool parameters:

Minimal mode (minimal=True): Returns only id, title, lat, lon, dataset_id
Basic mode: Adds year, catalog_id
Detail mode (default): Includes theme, metadata, hasThumbnail

Read the full file on GitHub · 222 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.

9d ago First seen · 222 lines · 1,811 tokens per session scan A ada89d09365e

Subscribe to this mod's changes

kklab-mlit-dpf-mcp CLAUDE.md is an instructions file published in the GitHub repository kkawailab/kklab-mlit-dpf-mcp (0 stars, last pushed 9mo ago), licensed MIT. It adds 1,811 tokens to every session, about $0.0091 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.

Data and AI

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

kklab-mlit-dpf-mcp: Instructions file for Claude Code