Amap logo

Amap

Organization
nano-muse
amap

Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Use when the user asks how far, how long, how to get somewhere (car, transit, bike, foot), what is near a place, or about the weather in a Chinese city.

Overview

Publishernano-muse
RepositorynanoMuse
Skill nameamap
Stars
885
Forks
94
Bundled files
Instructions only
LicenseGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by nano-muse on GitHub. Read the source before you install it.

Installation

Install the Amap AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/amap
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/nano-muse/nanoMuse.git /tmp/nanoMuse
mkdir -p .claude/skills
cp -r /tmp/nanoMuse/nanomuse/skills/builtin/amap .claude/skills/amap
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Amap in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Amap on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Amap is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

高德地图 (Amap) through MCP

高德 publishes an MCP server with twelve tools; configured, they appear to you as amap__maps_*. No browser, no phone, no screenshots: a question about a place is one or two tool calls.

Is it there?

Look for amap__maps_geo in your tools. If it is not there, say so in one line and give the user the four lines to add to config.toml, then stop. Your tools list is the only place it can be: do not run shell commands or scripts to look for it, and when the user asked for an app on their phone and you have read it there, the answer is complete without this skill:

toml
[[mcp.servers]]
name = "amap"
url = "https://mcp.amap.com/mcp?key={{vault:AMAP_KEY}}"   # a free Web 服务 key from console.amap.com
risk = "safe"

and nanomuse vault set AMAP_KEY. Without Node, the hosted URL is the way; with it, command = "npx", args = ["-y", "@amap/amap-maps-mcp-server"], env = { AMAP_MAPS_API_KEY = "{{vault:AMAP_KEY}}" } does the same.

The tools

  • amap__maps_geo: an address or a landmark (北京南站, 上海市浦东新区世纪大道100号) → coordinates lng,lat; amap__maps_regeocode the other way round. Almost everything else wants coordinates, so this comes first.
  • amap__maps_text_search: places by keyword (咖啡, 汉庭酒店) in a city; amap__maps_around_search, the same within radius metres of a location; amap__maps_search_detail, one place's details by its id (opening hours, rating, phone, address).
  • amap__maps_direction_driving, amap__maps_direction_walking, amap__maps_bicycling: a route between two coordinates with distance, duration and the steps; amap__maps_direction_transit_integrated, bus, metro and train together, and across cities with city and cityd.
  • amap__maps_distance: just the distance and time between points (type 1 = driving, 3 = straight line).
  • amap__maps_weather: today and the next few days for a city name or adcode.

Coordinates are 经度,纬度 (longitude first, GCJ-02). Durations come in seconds and distances in metres: say them as minutes and kilometres.

How to answer

  • Resolve both ends first, then one route call per mode the user cares about. When they did not say how they travel, compare transit and driving in one line each and say which you would take at that hour.
  • A "what's near" question: geocode the centre, one around_search, then give three places at most with what makes each worth it (rating, distance, open now), not the whole list.
  • Travel time is an estimate for now; for a departure later or tomorrow say so, and for a real day-of-travel plan add slack.
  • Weather goes into plans the user is making (an outdoor day, a trip) without being asked when it changes the plan (rain on the day of the hike).

With the other hands

  • 高德 + 12306: the route to the station (this skill) and the train itself (the train-tickets skill on the phone) make one plan: leave home at 07:10, G1 at 08:00.
  • 高德 + 飞书: a route or an address the user wants to share goes to a colleague with the feishu skill; a meeting's location is checked before the event is created.
  • 高德 + the workspace: a day's itinerary with places, times and the routes between them is a page in trips/, written with the trip-plan skill; the coordinates and distances come from here.

Finish

A few lines: where, how far, how long, by what, and the weather when it matters. Save nothing unless asked. remember the user's home and workplace once they name them, so that the next "how long to get to …" needs no question.

Frequently asked questions

What does the Amap AI skill do?

Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Use when the user asks how far, how long, how to get somewhere (car, transit, bike, foot), what is near a place, or about the weather in a Chinese city.

Why use Amap on TypingMind?

Because you install it once and use it with any model. Amap is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Amap in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/amap. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Amap?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Amap?

As many as you like. As long as a model supports skills, you can use Amap with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Amap AI skill free?

Yes. It is published on GitHub by nano-muse under the GPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇