inavi-mcp: Instructions file for Claude Code

CLAUDE.md

inavi-mcp CLAUDE.md is an instructions file for Claude Code from inavi-systems/inavi-mcp. It costs 2,421 tokens per session, scanned A, original, MIT.

Repository-specific instructions for inavi-mcp, a TypeScript Model Context Protocol server that connects AI assistants to iNavi Maps. It provides map-visualisation examples and iNavi API specifications through a standard input/output connection.

In plain words
What is it for?
Use it when developing, building, testing, or reviewing the server, including its map visualisation templates, API reference tools, strict TypeScript code, and Vitest tests.
Why use it?
It tells a coding agent how this map server works, which transport and validation tools it uses, and which commands run or test it.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is inavi-systems/inavi-mcp's own configuration. It tells Claude Code how to work on inavi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything inavi-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to inavi-systems/inavi-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/inavi-systems/inavi-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/inavi-systems/inavi-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.

agentmods badge for inavi-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inavi-systems/inavi-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/inavi-systems/inavi-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/inavi-systems/inavi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/inavi-systems/inavi-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.

agentmods 80×15 button for inavi-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/inavi-systems/inavi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/inavi-systems/inavi-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,421 This file is loaded in full into every session.
When invoked 2,421 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02421 $0.02421
Opus 5.5 $0.00968 $0.00968
Sonnet 5.5 $0.00484 $0.00484
Haiku 4.5 $0.00242 $0.00242

Measured 8d ago against content hash 867a3905a38f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

inavi-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 8d 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 · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 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 TypeScript MCP (Model Context Protocol) server that integrates with INAVI Maps API. It communicates with MCP Hosts (Claude Desktop, Cursor, etc.) via stdio transport (not HTTP), providing map visualization tools and API specifications.

Project Purpose: Enable AI assistants to work with geospatial data and visualize results on interactive maps through:

  1. HTML Example Tools: Code templates for custom map visualizations
  2. API Spec Tools: INAVI Maps API specifications for reference

Key Technology Stack:

  • TypeScript with strict type checking
  • MCP SDK (@modelcontextprotocol/sdk) for MCP Host integration
  • Zod for runtime validation
  • stdio transport (no Express/HTTP server needed for MCP functionality)

Common Commands

Development

npm run dev          # Development mode with hot reload
npm run build        # Compile TypeScript to JavaScript
npm start            # Run compiled server

Testing

npm test             # Run all tests with Vitest
npm run test:ui      # Run tests with Vitest UI
npm run test:coverage # Run tests with coverage report
npm run test:watch   # Run tests in watch mode

Code Quality

npm run lint         # Check code style
npm run lint:fix     # Auto-fix linting issues
npm run format       # Format code with Prettier
npm run format:check # Check formatting
npm run type-check   # TypeScript type checking without emit (src + test)

API Docs

npm run update-api-docs   # Update API documentation
npm run validate-api-docs # Validate API documentation

SDK Docs

npm run update-sdk-docs   # Scrape Web JS SDK docs (Docma) into public/sdk-docs/

Release

Releases run from GitHub Actions, not the shell. npm run release only prints a pointer and exits 1; release:minor and release:major do not exist.

Actions > Release > Run workflow > version-type: patch | minor | major | none

Read the full file on GitHub · 212 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. 8d ago Changed · +1 lines · +21 tokens per session 867a3905a38f
  2. 20d ago Changed · -5 tokens per session f0197b79fbfd
  3. 1mo ago Changed · +85 lines · +1,254 tokens per session f0bd33154dbd
  4. 2mo ago First seen · 126 lines · 1,151 tokens per session scan A 5c436d9dedb1

Subscribe to this mod's changes

inavi-mcp CLAUDE.md is an instructions file published in the GitHub repository inavi-systems/inavi-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 2,421 tokens to every session, about $0.0097 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.

Related

inavi-mcp CLAUDE.md compared with instructions from other repositories

inavi-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
inavi-mcp CLAUDE.mdinavi-systems/inavi-mcpInstructions file09d agoMITA2,421Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot