QCX
Language to Maps
What is QCX?
QCX is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to language to maps
Language to Maps
This server falls under the APIs category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Language to Maps
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx qcxConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use QCX
QCX is a language-to-maps application that lets users describe geographic queries in natural language and receive interactive Mapbox map results. It integrates a Mapbox MCP server powered by Composio to expose geocoding, distance calculation, nearby place search, and map link generation as AI-accessible tools. Built on Next.js with the Vercel AI SDK and Grok-3-mini as the language model, QCX is designed for developers exploring conversational map interfaces and location-aware AI agents.
Prerequisites
- Bun package manager installed (bun.sh)
- A Mapbox account with an access token (mapbox.com)
- A Composio account for the server-side Mapbox integration (composio.dev)
- An XAI API key for the Grok-3-mini model (platform.openai.com)
- A Tavily API key for web search (app.tavily.com)
Clone the repository and install dependencies
Clone the QCX repository and install all dependencies using Bun.
git clone https://github.com/QueueLab/QCX.git
cd QCX
bun installConfigure environment variables
Copy the example environment file and populate all required keys for the AI, mapping, search, and caching services.
cp .env.local.example .env.localSet required environment variables
Edit .env.local to add your API keys. All fields are required for the full feature set.
XAI_API_KEY=your-xai-api-key
TAVILY_API_KEY=your-tavily-api-key
UPSTASH_REDIS_REST_URL=https://your-redis.upstash.io
UPSTASH_REDIS_REST_TOKEN=your-redis-token
NEXT_PUBLIC_MAPBOX_ACCESS_TOKEN=your-mapbox-token
COMPOSIO_MAPBOX_AUTH_CONFIG_ID=your-composio-auth-config-id
COMPOSIO_USER_ID=your-composio-user-emailBuild and run the development server
Build the project and start the local development server. The app will be accessible at http://localhost:3000.
bun run build
bun run devTest map tool execution
Open http://localhost:3000 and enter a natural language geographic query. The server will call the Mapbox MCP tools (geocode, distance, nearby search) via Composio and render results on the map.
QCX Examples
Client configuration
The QCX Mapbox MCP server uses Composio integration and environment-based configuration. Below is the environment setup for the MCP tools.
{
"mcpServers": {
"qcx-mapbox": {
"command": "bun",
"args": ["run", "mapbox_mcp/server.ts"],
"env": {
"COMPOSIO_MAPBOX_AUTH_CONFIG_ID": "your-auth-config-id",
"COMPOSIO_USER_ID": "[email protected]",
"MAPBOX_ACCESS_TOKEN": "your-mapbox-access-token"
}
}
}
}Prompts to try
Natural language queries that QCX converts to Mapbox map operations.
- "Show me coffee shops near the Eiffel Tower in Paris."
- "How far is it from New York City to Boston?"
- "Geocode 1600 Pennsylvania Avenue, Washington DC."
- "Generate a map link centered on Tokyo."
- "Find hospitals within 2 km of downtown Chicago."Troubleshooting QCX
Map does not render or shows a blank screen
Verify that NEXT_PUBLIC_MAPBOX_ACCESS_TOKEN is set correctly in .env.local and is a valid public token from your Mapbox account. Public tokens must be prefixed with 'pk.'.
Composio MCP tool calls fail with authentication errors
Confirm that COMPOSIO_MAPBOX_AUTH_CONFIG_ID and COMPOSIO_USER_ID are set to the values from your Composio dashboard. These must match the auth config you created for the Mapbox integration in Composio.
AI responses are slow or the app fails to start
Ensure your Upstash Redis credentials are correct — the app uses Redis for caching and will fail to start without a valid connection. Check UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN.
Frequently Asked Questions about QCX
What is QCX?
QCX is a Model Context Protocol (MCP) server that language to maps It connects AI assistants to external tools and data sources through a standardized interface.
How do I install QCX?
Follow the installation instructions on the QCX GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with QCX?
QCX works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is QCX free to use?
Yes, QCX is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
QCX Alternatives — Similar APIs Servers
Looking for alternatives to QCX? Here are other popular apis servers you can use with Claude, Cursor, and VS Code.
Kong
★ 43.4k🦍 The API and AI Gateway
API Mega List
★ 5.4kThis GitHub repo is a powerhouse collection of APIs you can start using immediately to build everything from simple automations to full-scale applications. One of the most valuable API lists on GitHub—period. 💪
Fetch
★ 5.4kFetch web content and convert to markdown for AI consumption
Fusio
★ 2.1kSelf-Hosted API Management for Builders
Korean Law
★ 1.8k국가법령정보MCP v4.0 | 법제처 41개 API → 17개 MCP 도구. 법령·판례·조례 검색 + LLM 환각 방지 인용검증 + 조문 영향 그래프(impact_map) + 시점 비교 자동 diff(time_travel) + 시민 5단계 실행 가이드(action_plan) | 41 Korean legal APIs → 17 MCP tools
RuleGo
★ 1.5k⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
Browse More APIs MCP Servers
Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up QCX in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use QCX?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.