TravelMind MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TravelMind MCP Serverfind restaurants near 116.481,39.990 within 1000 meters"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TravelMind MCP Server
TravelMind (差旅 + 报销 + AI Agent 一体化) 的官方 MCP (Model Context Protocol) server。
让任意 MCP 兼容客户端(Claude Desktop / Cursor / WorkBuddy / 等)直接调用中国境内的差旅核心能力:地理编码、POI 搜索、周边搜索和反向地理编码。
Features
4 个核心 Tools,全部由高德开放 API 提供实时数据:
Tool | Description | API |
| 地址 → 经纬度 (城市/地址解析) |
|
| 经纬度 → 行政区 + POI (逆地理编码) |
|
| 关键词搜 POI (酒店/餐厅/景点) |
|
| 周边搜 POI (坐标 + radius) |
|
Related MCP server: AMap Maps MCP Server
Quick Start
Prerequisites
Node.js >= 18
高德开放平台 API Key: https://lbs.amap.com/dev/key/app
Install
git clone https://github.com/gcszkjpzzv-beep/TravelMind_MCP.git
cd TravelMind_MCP
npm installConfigure
export AMAP_API_KEY="your-amap-api-key"Run
node index.jsUse in Claude Desktop / Cursor
{
"mcpServers": {
"travelmind": {
"command": "node",
"args": ["/path/to/TravelMind_MCP/index.js"],
"env": { "AMAP_API_KEY": "your-key" }
}
}
}Tools Reference
geocode
{
"address": "北京市朝阳区望京 SOHO",
"city": "北京"
}Returns { location: "lng,lat", formatted_address, ... }.
regeocode
{ "location": "116.481,39.990" }Returns { formatted_address, addressComponent: { province, city, district, ... } }.
text_search
{
"keywords": "希尔顿酒店",
"city": "北京",
"types": "住宿"
}Returns { pois: [{ id, name, address, location, ... }] }.
around_search
{
"keywords": "餐厅",
"location": "116.481,39.990",
"radius": "1000"
}Returns { pois: [...] } within radius.
About TravelMind
Official site: https://www.trvaelmind.online
ICP: 浙ICP备2026021219号
License
MIT
Available Tools
4 toolsaround_searchBInspect
在坐标 + radius 范围内搜周边 POI,例如酒店附近 1km 内的餐厅。
| Name | Required | Description | Default |
|---|---|---|---|
| types | No | 可选 POI 大类 | |
| radius | No | 搜索半径(米),默认 1000,最大 50000 | |
| keywords | No | 可选关键词,例如 '餐厅' / '咖啡厅' | |
| location | Yes | 中心点经纬度 'lng,lat' |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must fully disclose behavior, but it only states the basic search operation. It does not mention important traits like rate limits, authentication requirements, or result ordering. The example adds some context but lacks depth.
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 extremely concise with a single sentence and an example, no redundant words. It front-loades the core functionality efficiently.
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 the tool's simplicity, the description covers the basic purpose but lacks details about output format, error conditions, and behavioral limits. The absence of an output schema means the agent must assume the response structure. It is minimally complete for basic use.
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 descriptions cover all parameters, so the baseline is 3. The description reinforces parameter usage through an example (keywords '餐厅', radius 1km) but does not add new semantic constraints beyond the schema. The integration of parameters into the action is slightly enhanced.
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 description clearly states the tool searches for nearby POIs (point of interest) given a coordinate and radius, with an illustrative example. This unambiguous action separates it from sibling tools like geocode and regeocode which handle coordinate conversions. The purpose is specific and easy to understand.
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?
No guidance is provided on when to use this tool over alternatives like text_search. The description only explains what the tool does without mentioning prerequisites, limitations, or use cases. An agent would need to infer from context when to choose this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
geocodeAInspect
将结构化地址解析为经纬度坐标,例如 '北京市朝阳区望京 SOHO' → location 'lng,lat'。
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | 可选,指定查询城市以提高准确度,例如 '北京' | |
| address | Yes | 待解析的结构化地址,例如 '北京市朝阳区望京 SOHO' |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses core behavior (parsing address to lng,lat coordinate string) and output format via example. However, it does not address edge cases (e.g., unresolved address, multiple matches) or any limitations.
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?
Single sentence with an example, no redundant words. Information is front-loaded and efficiently communicated.
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?
For a simple geocoding tool with no output schema, the description adequately explains input and output. It lacks details on error handling or result format variations, but the example compensates partially. Given no annotations, it is reasonably complete.
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 100% with descriptions for both parameters. The tool description adds no additional parameter meaning beyond what the schema already provides (e.g., city is optional, address is structured). Baseline 3 is appropriate.
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?
Description clearly states the verb ('解析', parse/resolve) and resource ('结构化地址' to '经纬度坐标'), with a concrete example. It distinguishes from sibling tools: 'regeocode' (reverse), 'text_search', 'around_search' by being specifically address-to-coordinates.
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?
Description implies usage context (structured address to coordinates) but does not explicitly state when to use this vs. alternatives like 'regeocode' or 'text_search'. No exclusions or comparison given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
regeocodeAInspect
将经纬度坐标转换为行政区划地址(街道级精度)。例如 '116.481,39.990' → '北京市朝阳区望京街道...'
| Name | Required | Description | Default |
|---|---|---|---|
| radius | No | 可选,搜索半径(米),默认 1000 | |
| location | Yes | 经纬度坐标,格式 'lng,lat' 例如 '116.481,39.990' |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so description must bear full burden. It only states the conversion and precision level, but omits important behavioral traits like coverage area, error handling, rate limits, or response format. Minimal disclosure.
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?
Very concise: one sentence plus example. No fluff, but could be better structured with bullet points for readability. Still efficient.
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, description should hint at return value (e.g., address components). It doesn't. Schema covers params well, but overall completeness is adequate but not thorough.
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 100%, so baseline accuracy. Description reinforces the location format with an example but adds no new meaning beyond the schema's descriptions. Radius is explained in schema; description doesn't enhance it.
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?
Description clearly states the tool converts coordinates to administrative address with street-level precision, and provides a concrete example. It distinguishes from sibling tools (geocode, text_search, around_search) by its reverse-geocoding nature.
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 implies the tool is for reverse geocoding, and sibling names suggest different functionalities. However, no explicit guidance on when to use versus when not to, or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
text_searchAInspect
在指定城市内按关键词搜 POI(酒店/餐厅/景点/地标)。返回前 10 条。
| Name | Required | Description | Default |
|---|---|---|---|
| city | Yes | 查询城市,例如 '北京'(必填以提高准确度) | |
| types | No | 可选 POI 大类,例如 '住宿' / '餐饮' / '购物'(高德 types 编码) | |
| keywords | Yes | 搜索关键词,例如 '希尔顿酒店' / '星巴克' |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the result limit (top 10) but does not mention other behaviors such as ordering, error handling, or auth requirements. This partial disclosure earns a 3.
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 a single, concise sentence that communicates the essential purpose and result limit with no extraneous words. It is well-structured and front-loaded.
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 the absence of an output schema and annotations, the description is adequate but not complete. It explains the basic functionality and result limit but lacks details on response structure, error behavior, or interaction between parameters. With three siblings, more comparative context would help.
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 100% with descriptions for each parameter. The description reiterates the purpose of city and keywords but adds no new semantics beyond the schema. The types parameter is already explained in the schema.
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 description clearly states the tool searches for POIs (hotels, restaurants, attractions, landmarks) by keyword within a specified city and returns the top 10 results. This distinguishes it from siblings like geocode (address to coordinates) and around_search (location-based search).
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 implies usage for keyword-based POI search within a city but does not explicitly state when to use this tool over alternatives like around_search. No guidance on prerequisites or exclusions is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
4 tool updates
v0.1.0- First observed
around_search - First observed
geocode - First observed
regeocode - First observed
text_search
TDQS
All four tools have clearly distinct purposes: geocode converts address to coordinates, regeocode does the reverse, text_search searches POIs by keyword in a city, and around_search finds POIs near a coordinate. No overlap or ambiguity.
All tool names follow a consistent snake_case pattern with descriptive verbs (geocode, regeocode, text_search, around_search). The use of 'regeocode' as a prefix variant is coherent within the domain.
The server has 4 tools, which is perfectly scoped for a geocoding and POI search service. Each tool covers a fundamental operation without being excessive or insufficient.
The tool set covers forward and reverse geocoding as well as two common POI search modes (keyword and proximity). A minor gap is the lack of a tool to retrieve details for a specific POI, but the existing tools still provide useful results.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Geoapify MCP — wraps the Geoapify Location Platform (geoapify.com)
Google Maps MCP Pack — geocoding, places, directions, distance matrix, elevation.
Geo MCP — geographic utilities from free public APIs
Remote MCP server for China brand visibility, destination demand, and KOL discovery workflows.
Related MCP Servers
- AlicenseCqualityDmaintenanceProvides access to Google Maps API functionality including geocoding, place search, direction routing, and distance calculations through a structured MCP interface.46MIT
- AlicenseAqualityCmaintenanceEnables location-based services through AMap/AutoNavi Maps API including geocoding, weather information, route planning, and POI searches. Supports multiple transportation modes and provides detailed geographic data for Chinese locations.123Mulan Permissive Software , Version 2
- FlicenseBqualityDmaintenanceEnables AI assistants to perform IP geolocation and nearby place searches using the Amap (Gaode Maps) API in China.212-
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that wraps the Amap (高德地图) Web Service APIs, giving AI assistants like Claude Code 9 map tools: geocoding, route planning (driving/transit/walking/cycling), POI search, nearby search, distance measurement, and IP location.1237MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gcszkjpzzv-beep/TravelMind_MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server