mcp-marketplace

MCP地图位置

提供方 AI-Agent-Hub

地图位置 stdio · 本地进程 未标注 社区 / 第三方 Claude DesktopClaudeCursorGemini CLI
查看接入方式

Open MCP Marketplace is an open-source project designed to simplify the integration of MCP servers into AI agent workflows, supporting tools like search, financial data analysis, and map planning.

一句话选型结论

按资料字段整理

mcp-marketplace 属于地图位置类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类地图位置 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 1 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

地图位置
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

Local Deployment AI Agent Tool Integration Open Source Data Analysis Map Services

支持客户端

适用场景

Local DeploymentAI AgentTool Integration

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
pip install mcp-marketplace

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
地址与路线

查地址、算路线、找附近地点。

位置检索

按区域筛门店、站点与设施。

地理数据

拉取经纬度、行政区等地理信息。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在地图位置场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
mcp-marketplace当前 未标注 stdio · 本地进程 本地部署 有 2026-04-10
MCP Server C2f246e3 20 stdio · 本地进程 本地部署 有 2026-05-17
OpenStreetMap MCP Server 12 stdio · 本地进程 本地部署 有 2026-05-18
Baidu Maps 10 stdio · 本地进程 本地部署 有 2026-05-17
Google Maps (google-maps-aa2563d3) 7 未标注 未标注 无 2026-05-17
generative-ai 未标注 stdio · 本地进程 本地部署 有 2026-04-17

服务器档案

地图位置
字段来自项目仓库与公开索引,中文说明由本站标注
提供方AI-Agent-Hub上游标注的维护方 AI-Agent-Hub
分类地图位置本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-04-10上游最后核验时间

详细介绍

19.2 KB
来自项目仓库与上游目录的原文,未做删改

Open MCP Marketplace · AI Agent Store Marketplace Index · OneKey MCP Router · AI Agent & MCP Moneytization Revenue Sharing plans · MCP Tool Use Agent from DeepNLP

WeChat

Visit the website MCP Tool Use Agent App to explore MCP Servers with sota agentic AI Search/Deep Research, Finance Data,Chart Creation, Excel Spreadsheet/Powerpoint usage.

MCP Open Marketplace and Search Engine

MCP Tool Use Agent App

Basic

Open MCP Marketplace is an open source project aims to make MCP Servers integration into your AI Agent Workflow Easier.

  • MCP Search Engine and Marketplace: MCP Marketplace Index and MCP Search Engine
  • MCP OneKey Router Use Just One Access Key to Authenticate and Use commercial MCPs, AI Agent & MCP Moneytization Revenue Sharing plans: OneKey MCP Router introduction and proxy Onekey MCP servers App.
  • MCP Server Tool Meta and Config: You can get well-cleaned up MCP Servers Tools Meta information, Tools and Config Schema, etc.
  • Web Based MCP Client with Admin Page: Similar to Claude Desktop, Cursor, and many other clients, Open MCP-Marketplace provides a pured web based MCP client and Admin Page to connect(Start/End) and use MCP tools.
  • Agent ToolBox: Explore, Search Various 11k+ MCP Servers from open mcp marketplace. You can also filter by category, such as official, browser use, map, finance, coding, office software usage, etc.
  • Various AI Agent Apps Support: You can easily integrate the app into your existing Chatbot, AI Search/Deep Research Engine, Excel Spreadsheet/Powerpoint Creation, Video/Image generation, Coding IDE, etc.
  • Public API Access: Visit API Documentation to search related mcp server and tools by keywords, category and more.
  • MCP Tool Use Agent and Workflow App: MCP Tool Use Agent Source Code
  • Python/Typescript Package Support: Pypi, Npm

News

  • Multi-Agent Parallel Running: Parallel Running Multi Agents is alive, You can call 3-5 trip/planning, deep research agents at the same time.
  • CLI mcpm: Command Line tool to start a python based MCP Client from your mcp_config.json, like cursor/Claude. Useful for MCP Benchmarking which provides rest APIs endpoint.
  • OneKey MCP Router: Use OneKey to Access commercial MCPs. Visit OneKey MCP Router for details.
  • Upgraded: Office File Agent and Visualization Agent: Excel spreadsheet data writing and data analysis agent, Powerpoint generation, Charts Creation. Excel Spreadsheet Agent, Visualization Agent
  • Live MCP Tool Use Agent is Online, Visit the MCP Tool Use Agent App to see the workflows

Example MCP Usage by Categories

Domain Related MCP Server Demo
Office File Agent Excel Spreadsheet, Powerpoint, PDF, etc Example MCP
AI Search/Deep Research Bing/Google Custom/Perplexity/Tavily/Firecrawl Demo MCP
Map Trip Planning GoogleMap, Amap(Gaode), BaiduMap, etc. Example MCP Use MCP
Browser Usage Playwright, Puppeteer, etc. Demo MCP
Chart,Graph,Image Gemini NanoBanana3,everart,mcp-server-charts(AntV),canva-mcp,bing-image-search-mcp Example MCP
Multi-Agent Parallel Running DeepSearch/Trip Planning Example

Example: Route Planning using Google Map MCP```
q=Find the best route from JFK Airport to Times Square in New York


**Example: Office Agent Excel Spreadsheet and Powerpoint Creation Usage**```
q=Write below information to an excel spreadsheet. Derek: male, graduated in years 2019, IT department, Jenifer: female graduated in 2024 Sales and Marketing department, Alan: male, graduated in 2021 in R&D department, Paul: mail, graduated in 2015, Staff in Operations department. Please formalize the data into three columns: name, graduation year and department. Then use spreadsheet formula to calculate the percentage of employees graduated within 3 years.

Excel Spreadsheet and Powerpoint Office Agent

Exmaple: Chart Plotting```
q=Plot a pie chart showing 25% of employees graduated within 3 years and 75% graduated more than 3 years ago.


Excel Spreadsheet and Powerpoint Office Agent

**Example: AI Search Deep Research**

Visit MCP Tool Use App

**Example: MCP Admin and Playground To Manage Tools and Servers**

Visit MCP Tool Use App

## KEY Features

1. MCP Server Public Index of Tools Schema and Config file
Dataset Collection of MCP Servers Tool/Function Call Schemas from 5000+ MCP servers, Useful for Tools RAG, Tools Dispatcher research and R&D. You can search route planning or "map" keywords from raw schema files. Welcome to add your config to the index. MCP Tool Schema

2. MCP Marketplace Web Integration, See Web Demo and Video how to integrate the Open MCP Marketplace to Your AI Search Engine or Agent Workflow.

- **Pure Web-based Plugin** : Show the Panel of MCP Tools from available open MCP marketplace, Support Filtering, Search, Installation

- **Browse Navigate and Pagination** : User can browser the MCP Tools by category and use pagination to navigate.

- **Customized MCP servers Selection and Installation** : Users can choose which MCP tools to perform tasks from mcp tools marketplace with similar features, such as Map Location, Search, Fetch, Payment, etc.

- **Badge**: Put Badge on your homepage Track MCP Servers User Reviews and Ratings, such as

3. MCP API Endpoint Support for Your AI Client Development

- **Various MCP Marketplace API Endpoint**: Get Server Schema, Such as pulsemcp.com, deepnlp.org, aiagenta2z.com,etc.

- **GET/UPDATE/CREATE** MCP Servers Meta information to get your MCP Server more visibilityy.

- **Python and Typescript SDK** Search and registry of MCP Servers and Tools

- **Rich Meta Data** Tools, Servers Description, URL, Category, Github stars, User reviews score, Ratings and more statistics.

4. Agent Workflow of MCP Marketplace
- **MCP Tools Dispatcher Agent**: The MCP Tool Dispatcher Agent helps to retrieve relevent tools from thousands of MCP servers and tools from marketplace, and reduce the context token length of function call LLM.

5. MCP Client support CLI `mcpm` to start mcp server From config file
- **Lightweight MCP Client**: Start the MCP Client just like cursor/Claude Desktop. (npx/python)
- **Benchmarking** : Support Rest APIs to run tool/call (Google-maps/perplexity/Deep Search Web clients,etc)

## 1. MCP Server Public Index of Tools Schema and mcp.config file

See MCP Tool Schema for details.

Collected tools schema from google map mcp```
{"name": "maps_geocode", "description": "Convert an address into geographic coordinates", "input_schema": {"type": "object", "properties": {"address": {"type": "string", "description": "The address to geocode"}}, "required": ["address"]}}
{"name": "maps_directions", "description": "Get directions between two points", "input_schema": {"type": "object", "properties": {"origin": {"type": "string", "description": "Starting point address or coordinates"}, "destination": {"type": "string", "description": "Ending point address or coordinates"}, "mode": {"type": "string", "description": "Travel mode (driving, walking, bicycling, transit)", "enum": ["driving", "walking", "bicycling", "transit"]}}, "required": ["origin", "destination"]}}

2. MCP Marketplace Web Client Integration

MCP Tool Use Agent

MCP Marketplace Browse and Pagination of MCP Servers Demo

3. Various API Endpoint Support for Your AI Client Development

Supported MCP Marketplace API Provider

Endpoint API Website
deepnlp.org https://www.deepnlp.org/api/mcp_marketplace/v1 https://www.deepnlp.org/doc/mcp_marketplace
pulsemcp.com https://api.pulsemcp.com/v0beta/servers https://www.pulsemcp.com/api

Python and Typescript SDK

For official documentation of MCP Marketplace API, please check https://www.deepnlp.org/doc/mcp_marketplace
, Python SDK and Typescript SDK (WIP)

Installation```
pip install mcp-marketplace

**Usage**

#### Search MCP Server

Search MCP Server by Meta Information by unique id, query or category```
import mcp_marketplace as mcpm

## endpoint: deepnlp
mcpm.set_endpoint("deepnlp")
result = mcpm.search(query="map", page_id=0, count_per_page=20, mode="dict")
print (result)

server_id = "financial-datasets/mcp-server"
result2 = mcpm.search(query="financial datasets", count_per_page=20, offset=0)
print (result2)

## Search By Unique ID:  e.g. github {owner_name}/{repo_name}
result_id = mcpm.search(id="puppeteer/puppeteer", mode="list", page_id=0, count_per_page=100, config_name="deepnlp")

# search by batch query
query_list = ["map", "navigation", "route planning"]
params_list = [{"query": query, "page_id":0, "count_per_page":50} for query in query_list]
results = mcpm.search_batch(params_list)

Curl Endpoint```
curl https://www.deepnlp.org/api/mcp_marketplace/v1/server/google-maps/google-maps


**Result**```
{
  "total_hits": 1,
  "id": "google-maps/google-maps",
  "items": [{
    "content_name": "Google Maps",
    "publisher_id": "pub-google-maps",
    "website": "https://github.com/modelcontextprotocol/servers/tree/main/src/google-maps",
    "review_cnt": "2",
    "rating": "4.5",
    "description": "Google Maps  Location services, directions, and place details\r\n\r\n# Google Maps MCP Server\r\n\r\nMCP Server for the Google Maps API.\r\n\r\n## Tools\r\n\r\n1. \\`maps_geocode\\`\r\n\r\n   - Convert address to coordinates\r\n   - Input: \\`address\\` (string)\r\n   - Returns: location, formatted_address, place_id\r\n\r\n2. \\`maps_reverse_geocode\\`\r\n\r\n   - Convert coordinates to address\r\n   - Inputs:\r\n     - \\`latitude\\` (numb",
    "ext_info": {
      "tools": []
    },
    "subfield": "MAP",
    "field": "MCP SERVER",
    "id": "google-maps/google-maps",
    "content_tag_list": "official",
    "config": [],
    "thumbnail_picture": "https://118.190.154.215/scripts/img/ai_service_content/b7fe82a3ab985ce1a953f7b4ad9c5e01.jpeg"
  }]
}

List Available Tools```

import mcp_marketplace as mcpm

server_id = "google-maps/google-maps"
result = mcpm.list_tools(id=server_id, config_name="deepnlp_tool")

server_id = "puppeteer/puppeteer"
result = mcpm.list_tools(id=server_id, config_name="deepnlp_tool")


**Curl Endpoint**```
curl https://www.deepnlp.org/api/mcp_marketplace/v1/tools/google-maps/google-maps
``````
{"id":"/google-maps/google-maps","tools":[{"name":"maps_geocode","description":"Convert an address into geographic coordinates","input_schema":{"type":"object","properties":{"address":{"type":"string","description":"The address to geocode"}},"required":["address"]}},{"name":"maps_reverse_geocode","description":"Convert coordinates into an address","input_schema":{"type":"object","properties":{"latitude":{"type":"number","description":"Latitude coordinate"},"longitude":{"type":"number","description":"Longitude coordinate"}},"required":["latitude","longitude"]}},{"name":"maps_search_places","description":"Search for places using Google Places API","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query"},"location":{"type":"object","properties":{"latitude":{"type":"number"},"longitude":{"type":"number"}},"description":"Optional center point for the search"},"radius":{"type":"number","description":"Search radius in meters (max 50000)"}},"required":["query"]}},{"name":"maps_place_details","description":"Get detailed information about a specific place","input_schema":{"type":"object","properties":{"place_id":{"type":"string","description":"The place ID to get details for"}},"required":["place_id"]}},{"name":"maps_distance_matrix","description":"Calculate travel distance and time for multiple origins and destinations","input_schema":{"type":"object","properties":{"origins":{"type":"array","items":{"type":"string"},"description":"Array of origin addresses or coordinates"},"destinations":{"type":"array","items":{"type":"string"},"description":"Array of destination addresses or coordinates"},"mode":{"type":"string","description":"Travel mode (driving, walking, bicycling, transit)","enum":["driving","walking","bicycling","transit"]}},"required":["origins","destinations"]}},{"name":"maps_elevation","description":"Get elevation data for locations on the earth","input_schema":{"type":"object","properties":{"locations":{"type":"array","items":{"type":"object","properties":{"latitude":{"type":"number"},"longitude":{"type":"number"}},"required":["latitude","longitude"]},"description":"Array of locations to get elevation for"}},"required":["locations"]}},{"name":"maps_directions","description":"Get directions between two points","input_schema":{"type":"object","properties":{"origin":{"type":"string","description":"Starting point address or coordinates"},"destination":{"type":"string","description":"Ending point address or coordinates"},"mode":{"type":"string","description":"Travel mode (driving, walking, bicycling, transit)","enum":["driving","walking","bicycling","transit"]}},"required":["origin","destination"]}}]}

List MCP Config files

API```
GET /api/mcp_marketplace/v1/server/${owner_id}/${repo_name}


## Resources

### Badage

Put Badge on your homepage markdown to track MCP Servers User Reviews and Ratings, such as .

change google-maps/google-maps to your MCP "owner_name"/"repo_name"```
![MCP Marketplace User Review Rating Badge](https://www.deepnlp.org/api/marketplace/svg?name=${owner_name}/${repo_name})](https://www.deepnlp.org/store/ai-agent/mcp-server/pub-${owner_name}/${repo_name})

## google map
![MCP Marketplace User Review Rating Badge](https://www.deepnlp.org/api/marketplace/svg?name=google-maps/google-maps)](https://www.deepnlp.org/store/ai-agent/mcp-server/pub-google-maps/google-maps)

4. Agent Workflow of MCP Marketplace

(WIP) Here is a diagram of how MCP Marketplace is integrated to your Agent Workflow```mermaid
graph TD
Start --> Search[Query Plan]
Search[Query Plan] --> QueryPlanning[Query Planning Agent]
QueryPlanning --> SearchTask1[Search]
SearchTask1 --> DocList[DocList]
DocList --> Generation

Search[Query Plan] --> ToolDispatcher[Tool Dispatcher Agent]
ToolDispatcher --> Task1[MCP Server 1]
ToolDispatcher --> Task2[MCP Server 2]
ToolDispatcher --> Task3[MCP Server 3]
Task1 --> Tool1[Tool List 1]
Task2 --> Tool2[Tool List 2]
Task3 --> Tool3[Tool List 3]

Tool1 --> LLM[LLM Function Call Agent]
Tool2 --> LLM[LLM Function Call Agent]
Tool3 --> LLM[LLM Function Call Agent]

LLM -->  ToolSelection

ToolSelection --> ToolResult[Tool Execution Result]

ToolResult --> Generation

### 5. MCP Client `mcpm` CLI tool for Personal Use or Benchmark Purpose

**Installation**

You can install the command line `mcpm` from mcp-marketplace pypi package, and start a MCP Client using local
`mcp_config.json` file```
## Basic Usage MCP Index and Search
pip install mcp-marketplace

## MCPClient Supports User Defined mcp_config.json, Just Like Other Clients Cursor/Claude
pip install mcp-marketplace[mcp_tool_use]

The CLI 'mcpm' will be in python path```
mcp run --host 0.0.0.0 --port 5000

Use Local Config File

cd python/tests

mcpm run --port 5000 --config "./mcp_config_onekey.json"

mcpm run --port 5000 --config "./mcp_config.json"


Then you can visit http://0.0.0.0:5000 for web console and
http://0.0.0.0:5000/mcp for mcp management

#### Benchmark

You can also run various MCP benchmark using the rest API From the Client

| API | Description                                                                      |
| ---- |----------------------------------------------------------------------------------|
| /api/query | The endpoint which you can post the tool parameters to get the tool/call results |

**CURL Tests**

Once you started the service and run the target mcp server, you can run the tools calls through the REST API.

Let's say you want to post to server: puppeteer and test tools: puppeteer_navigate to navigate chrome to a webpage.

Endpoint: http://127.0.0.1:5000/api/query```

curl -X POST -H "Content-Type: application/json" -d '{
    "server_id": "puppeteer",
    "tool_name": "puppeteer_navigate",
    "tool_input": {
        "url": "https://arxiv.org/list/cs/new"
    }
}' http://127.0.0.1:5000/api/query

Result```
{"success":true,"data":["Navigated to https://arxiv.org/list/cs/new"],"error":null}%


**REST GET/POST Request By Python/Typescript/etc**

For example, post request to MCP: amap-amap-sse, Tool: Get Weather and get local weather. You need to start mcp server 'amap-amap-sse' before running command line.

cd ./tests```
python run_mcp_request.py

## define input_params
        input_params = {
            "server_id": "amap-amap-sse",
            "tool_name": 'maps_weather',
            "tool_input": {
                "city": "乌鲁木齐"
            }
        }

Result{'success': True, 'data': ['{"city":"乌鲁木齐市","forecasts":[{"date":"2025-06-30","week":"1","dayweather":"多云","nightweather":"多云","daytemp":"31","nighttemp":"20","daywind":"西北","nightwind":"西北","daypower":"1-3","nightpower":"1-3","daytemp_float":"31.0","nighttemp_float":"20.0"},{"date":"2025-07-01","week":"2","dayweather":"多云","nightweather":"多云","daytemp":"28","nighttemp":"20","daywind":"西北","nightwind":"西北","daypower":"1-3","nightpower":"1-3","daytemp_float":"28.0","nighttemp_float":"20.0"},{"date":"2025-07-02","week":"3","dayweather":"多云","nightweather":"多云","daytemp":"28","nighttemp":"20","daywind":"西北","nightwind":"西北","daypower":"1-3","nightpower":"1-3","daytemp_float":"28.0","nighttemp_float":"20.0"},{"date":"2025-07-03","week":"4","dayweather":"多云","nightweather":"晴","daytemp":"30","nighttemp":"21","daywind":"西北","nightwind":"西北","daypower":"1-3","nightpower":"1-3","daytemp_float":"30.0","nighttemp_float":"21.0"}]}'], 'error': None}

Contribution

Resources

  • MCP Marketplace DeepNLP
  • MCP Marketplace PulseMCP
  • AI Agent Marketplace

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
mcp-marketplace 怎么安装?

在客户端按下面的安装命令接入:pip install mcp-marketplace。装完在客户端配置里引用同一个包或端点。

mcp-marketplace 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

mcp-marketplace 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

mcp-marketplace 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

mcp-marketplace 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Gemini CLI、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

mcp-marketplace 能提供哪些能力?

资料显示能力标签包括 Local Deployment、AI Agent、Tool Integration、Open Source、Data Analysis、Map Services。具体工具清单以官方文档为准。

mcp-marketplace 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

mcp-marketplace 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-04-10。