← 返回 Skills 市场

Google Maps Grounding MCP

Name: Google Maps Grounding MCP
Author: ryanbaumann

作者 ryanbaumann · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

4047

总下载

当前安装

版本数

在 OpenClaw 中安装

/install google-maps-grounding-lite-mcp

功能描述

Google Maps Grounding Lite MCP for location search, weather, and routes via mcporter.

使用说明 (SKILL.md)

Grounding Lite

Google Maps Grounding Lite MCP provides AI-grounded location data. Experimental (pre-GA), free during preview.

Setup

Enable the API: gcloud beta services enable mapstools.googleapis.com
Get an API key from Cloud Console
Set env: export GOOGLE_MAPS_API_KEY="YOUR_KEY"

Configure mcporter:

mcporter config add grounding-lite \
  --url https://mapstools.googleapis.com/mcp \
  --header "X-Goog-Api-Key=$GOOGLE_MAPS_API_KEY" \
  --system

Tools

search_places: Find places, businesses, addresses. Returns AI summaries with Google Maps links.
lookup_weather: Current conditions and forecasts (hourly 48h, daily 7 days).
compute_routes: Travel distance and duration (no turn-by-turn directions).

Commands

# Search places
mcporter call grounding-lite.search_places textQuery="pizza near Times Square NYC"

# Weather
mcporter call grounding-lite.lookup_weather location='{"address":"San Francisco, CA"}' unitsSystem=IMPERIAL

# Routes
mcporter call grounding-lite.compute_routes origin='{"address":"SF"}' destination='{"address":"LA"}' travelMode=DRIVE

# List tools
mcporter list grounding-lite --schema

Parameters

search_places: textQuery (required), locationBias, languageCode, regionCode

lookup_weather: location (required: address/latLng/placeId), unitsSystem, date, hour

compute_routes: origin, destination (required), travelMode (DRIVE/WALK)

Notes

Rate limits: search_places 100 QPM (1k/day), lookup_weather 300 QPM, compute_routes 300 QPM
Include Google Maps links in user-facing output (attribution required)
Only use with models that don't train on input data

安全使用建议

This skill appears coherent, but take these precautions before installing: 1) Verify the mcporter npm package and its maintainer (installing npm packages runs third-party code). 2) Prefer installing mcporter per-user rather than system-wide; avoid `--system` unless you intend global config and understand permissions. 3) Restrict your GOOGLE_MAPS_API_KEY in Cloud Console (enable only the required APIs, set HTTP referrer or IP restrictions, and set application restrictions) to limit blast radius if the key is leaked. 4) Ensure you have node/npm available and that installing mcporter fits your environment policy. 5) Be aware the config step stores the API key in mcporter headers—check where config files are written and who can read them. 6) Monitor usage/billing and quota limits for the Maps preview APIs. If you want lower risk, ask the skill author for a per-user config example (no --system) and the mcporter package repo URL to review source before installing.

功能分析

Type: OpenClaw Skill Name: google-maps-grounding-lite-mcp Version: 1.0.0 The skill is benign. It uses the `mcporter` tool to interact with the Google Maps Grounding Lite API, requiring a `GOOGLE_MAPS_API_KEY` for authentication, which is passed securely as an `X-Goog-Api-Key` header to `mapstools.googleapis.com/mcp`. Installation involves a standard `npm install mcporter` command, and setup instructions configure `mcporter` appropriately. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection attempts against the agent in the `SKILL.md` file; all instructions and commands are aligned with the stated purpose of providing Google Maps functionality.

能力评估

✓ Purpose & Capability

Name/description (Google Maps grounding via mcporter) align with declared requirements: mcporter binary and GOOGLE_MAPS_API_KEY are exactly what this skill needs to call the Maps Grounding MCP. The primary credential is appropriate and no unrelated credentials or config paths are requested.

ℹ Instruction Scope

SKILL.md stays on-topic (how to enable the Maps API, add the API key, configure mcporter, and call the listed tools). Two operational points to note: (1) it suggests using `gcloud beta services enable ...` but gcloud is not listed in required binaries; (2) the example uses `mcporter config add ... --system`, which writes system-level configuration (may require elevated privileges and affects global mcporter config). Neither is inconsistent with the purpose, but both are operational details the user should be aware of.

✓ Install Mechanism

The install spec installs the mcporter npm package (public registry) which is a typical mechanism for a CLI. This is a moderate-risk, expected install method; there are no downloads from arbitrary URLs or extract steps. The package and publisher should be validated before installation, but the mechanism itself is appropriate for the stated function.

✓ Credentials

Only GOOGLE_MAPS_API_KEY is required and declared as the primary credential — this is proportionate to a Maps-based skill. No extra secrets or unrelated environment variables are requested.

ℹ Persistence & Privilege

always:false and normal autonomous invocation are fine. The only persistence-related concern is the SKILL.md recommendation to run `mcporter config add ... --system` which creates system/global mcporter configuration; this may require higher privileges and will store the API key in a config header. The skill does not request persistent platform-level privileges or alter other skills.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install google-maps-grounding-lite-mcp
安装完成后，直接呼叫该 Skill 的名称或使用 /google-maps-grounding-lite-mcp 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of google-maps-grounding-lite. - Provides location search, current weather, and route computation via Google Maps AI-grounded APIs. - Integrates with mcporter CLI for quick setup and usage. - Includes three tools: search_places, lookup_weather, compute_routes. - Experimental, free during preview with usage rate limits. - Requires a Google Maps API key and mcporter installation.

元数据

Slug google-maps-grounding-lite-mcp

版本 1.0.0

许可证 —

累计安装 13

当前安装数 13

历史版本数 1

常见问题