将 GPS 坐标转换为 AI 可用的位置上下文 — 适用于 Claude Desktop、Claude Code 以及任何兼容 MCP 的助手。
发送坐标，获取地点名称、类别和实时营业时间：
{
"label": "Walmart",
"category": "supermarket",
"is_open": true,
"closes_at": "23:00",
"opening_hours": "Mo-Su 06:00-23:00"
}Claude 随后可以回答：“你现在在沃尔玛，47 分钟后关门。”
Related MCP server: Geo MCP Worker
在 geolabel.dev 免费获取 — 每天 100 次请求，无需信用卡。
在下方选择你的客户端。
编辑 ~/Library/Application Support/Claude/claude_desktop_config.json：
{
"mcpServers": {
"geolabel": {
"command": "uvx",
"args": ["geolabel-mcp"],
"env": {
"GEOLABEL_API_KEY": "glk_your_key_here"
}
}
}
}重启 Claude Desktop。GeoLabel 工具将出现在工具列表中。
claude mcp add geolabel -- uvx geolabel-mcp
export GEOLABEL_API_KEY=glk_your_key_here编辑 ~/.hermes/config.json：
{
"mcpServers": {
"geolabel": {
"command": "uvx",
"args": ["geolabel-mcp"],
"env": {
"GEOLABEL_API_KEY": "glk_your_key_here"
}
}
}
}更多信息请参阅 Hermes Agent MCP 文档。
# Register the server
openclaw mcp set geolabel \
--command uvx \
--args geolabel-mcp \
--env GEOLABEL_API_KEY=glk_your_key_here
# Verify it's registered
openclaw mcp list更多信息请参阅 OpenClaw MCP 文档。
You: I'm at 41.8827, -87.6233 — what's here and is it open?
Agent: You're at Planet Fitness (a gym). It's currently open and closes
at 11:00 PM tonight — you have about 3 hours left.get_location_label识别给定坐标 radius 米范围内最近的命名地点。
参数 | 类型 | 默认值 | 描述 |
| float | 必填 | 纬度 (-90 到 90) |
| float | 必填 | 经度 (-180 到 180) |
| int | 100 | 搜索半径（米，最大 500） |
响应字段：
字段 | 类型 | 描述 | |
| string | null | 来自 OpenStreetMap 的原始地点名称 |
| string | 清晰、可直接显示的名称 | |
| string | null | 稳定类型： |
| float | null | 从你的坐标到该地点的距离 |
| bool | null |
|
| string | null | 下次营业时间 |
| string | null | 今日关门时间 |
| string | null | 原始 OSM |
| bool | 从 10 分钟缓存中获取；营业时间始终实时重新计算 |
# pip
pip install geolabel-mcp
# run directly
GEOLABEL_API_KEY=glk_xxx geolabel-mcpclaude mcp add geolabel -- uvx geolabel-mcp然后设置你的密钥：
# add to your shell profile or .env
export GEOLABEL_API_KEY=glk_your_key_here变量 | 必填 | 描述 |
| 是 | 你的 GeoLabel API 密钥 |
| 否 | 覆盖 API 基础 URL（默认： |
GeoLabel 在数据写入磁盘前会从所有服务器日志中剔除坐标。不存储任何移动历史记录。数据实时处理并立即丢弃。完整隐私政策 →
MIT
Identify a place from GPS coordinates and return its label, category, and live opening-hours status.
Use this whenever the user provides coordinates or asks what is at a location. The response gives Claude everything needed to answer location-aware questions — place name, type, whether it is open right now, and when it closes or next opens.
Args: lat: Latitude in decimal degrees (-90 to 90). lng: Longitude in decimal degrees (-180 to 180). radius: Search radius in metres. Smaller values pin to the nearest place precisely; larger values cast a wider net. Default 100 m, maximum 500 m.
Returns a dict with: place Raw venue name from OpenStreetMap (may include branch numbers or location suffixes). Prefer 'label' for display. label Clean, user-friendly name — e.g. "Walmart", "Planet Fitness", "Starbucks". Use this for display and speech. category Stable place type for logic: "gym", "supermarket", "restaurant", "fast_food", "gas_station", "pharmacy", "hospital", "cafe", "retail", etc. distance_meters Distance in metres from the supplied coordinates to the matched place centroid. is_open true → currently open. false → currently closed. null → OpenStreetMap has no hours data for this place. opens_at Next opening time as "HH:MM" (24-hour). Populated when is_open is false so you know when it reopens. null when open, or when hours are unknown. closes_at Today's closing time as "HH:MM" (24-hour). Populated when is_open is true — subtract current time to get minutes remaining. null when closed or hours unknown. opening_hours Raw OpenStreetMap opening_hours string, e.g. "Mo-Fr 09:00-18:00; Sa 10:00-17:00". null if not set in OSM. cached true if place data was served from the 10-minute in-memory cache. Hours fields are always recalculated live against the current time, even on cache hits.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | ||
| lng | Yes | ||
| radius | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavior: radius interpretation, caching with 10-minute TTL, live recalculation of hours, and null handling for unknown hours. It discloses all behavioral traits beyond the basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with purpose, usage, parameters, and return fields. Every sentence adds value; no redundant or extraneous text. Front-loaded the key purpose in the first sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description completely documents all return fields with explanations, including edge cases like null values. All parameters are explained. The tool's behavior (caching, live hours) is fully covered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description provides detailed parameter semantics: lat/lng ranges, radius meaning with default and maximum, and concrete usage guidance. This goes far beyond the schema's minimal type information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The first sentence clearly states the tool identifies a place from GPS coordinates and returns label, category, and live opening-hours status. The verb 'identify' combined with the resource 'place' and specific outputs makes the purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this whenever the user provides coordinates or asks what is at a location.' This direct instruction tells the agent exactly when to invoke the tool, leaving no ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1get_location_labelScored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The single tool's purpose is clearly defined.
With only one tool, naming consistency is inherently perfect. The name 'get_location_label' follows a clear verb_noun pattern.
A single tool is at the low end of typical scope. It serves a focused purpose (geolocation labeling), but the server feels thin for a full MCP surface.
The tool provides rich detail (name, category, hours, distance) for its single operation. Lacks additional geolocation utilities like batch or address lookup, but core need is met.
Worldwide place search with coordinates (Open-Meteo) — paid per call (x402/credits), 1 tools
Nominatim MCP — wraps OpenStreetMap Nominatim geocoding API (free, no auth)
OpenTripMap MCP — wraps the OpenTripMap Places API (dev.opentripmap.org)
Geocoding, routing, isochrones, traffic, weather, and place search for AI agents. 19 MCP tools.