What are the runtime requirements?
Node.js 16 or higher, TypeScript 4.5 or higher, and a valid Mapbox API key are required.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mapbox-mcp-server": {
"command": "node",
"args": [
"/absolute/path/to/mapbox-mcp-server/build/index.js"
],
"env": {
"MAPBOX_ACCESS_TOKEN": "your-api-key"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The Mapbox MCP Server is a Model Context Protocol server that integrates with the Mapbox API, providing navigation and search tools for AI assistants like Claude Desktop. It is designed for developers who need to access Mapbox services—such as directions, matrices, and geocoding—through MCP-compatible clients.
Install Node.js 16+, TypeScript 4.5+, and obtain a Mapbox API key. Export the key as environment variable MAPBOX_ACCESS_TOKEN. Add the server configuration to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json) with the command pointing to the built server file. Invoke the provided MCP tools for navigation and search.
Node.js 16 or higher, TypeScript 4.5 or higher, and a valid Mapbox API key are required.
Follow the instructions at the Mapbox Account Access Tokens page (https://console.mapbox.com/account/access-tokens/) to generate an API key.
Directions API: 300 requests per minute. Matrix API: 60 requests per minute for driving/walking/cycling, 30 for driving-traffic. Geocoding API: 600 requests per minute.
Five tools: `mapbox_directions`, `mapbox_directions_by_places`, `mapbox_matrix`, `mapbox_matrix_by_places`, and `mapbox_geocoding`. Each accepts optional parameters for profile, language, and more.
The server uses a modular structure with handler base classes, a registry, and a main entry point. Source code is organized under `src/` with types, schemas, tool definitions, and handlers. Deployment involves building the TypeScript project and running the compiled `index.js`.
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
A search tool helps dev to solve the naming things problem.

Model Context Protocol Servers
Comments