Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Mapbox in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Drive Mapbox APIs (geocoding, directions, isochrones, matrix, tilequery) from any AI agent. 8 tools, access-token query auth.
Try asking
Example prompts for Mapbox
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Mapbox, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Mapbox + Gemini
Drive Mapbox APIs (geocoding, directions, isochrones, matrix, tilequery) from any AI agent. 8 tools, access-token query auth.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
MAPBOX_ACCESS_TOKEN
Step 1 — Get credentials
mapbox.com/api/).
Setup:
- Sign in to https://account.mapbox.com → Access tokens → Create a token.
- Pick scopes: usually
styles:read+fonts:read+geocoding+directions+matrix+isochrone+tilequery. - Copy the token (starts with
pk.). SetMAPBOX_ACCESS_TOKEN.
Authentication: query-string ?access_token=....
Coordinate convention (Mapbox-specific): longitude FIRST, then latitude. The order is lng,lat, NOT lat,lng like Google Maps. Trip up on this and your results land in the wrong country.
…(continued in the in-app connector instructions)
Step 2 — Install the adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Step 3 — Add the connector in Gemini
Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Get your MCP API key from AnythingMCP → Profile → MCP API Keys → New Key.
- Save the file and restart
gemini. - Run
/mcpinside the Gemini CLI —Mapboxshould be listed as available. - Vertex AI Studio: pass
https://cloud.anythingmcp.com/mcpto thetoolsarray of your request with the same Bearer header.
Available tools
| Tool | What it does |
|---|---|
mapbox_geocode_forward | Forward geocoding (address text → coordinates) |
mapbox_geocode_reverse | Reverse geocoding (coordinates → address) |
mapbox_directions | Compute driving / walking / cycling directions between waypoints |
mapbox_isochrone | Get the area reachable within N minutes from a starting point (an 'isochrone' — like 'how far can I drive in 15 min?') |
mapbox_matrix | Compute travel-time and distance MATRIX between many origins and destinations (e |
mapbox_static_image | Generate a static PNG/JPG map of a location with optional pin overlays |
mapbox_tilequery | Query features in a vector tileset at a specific point — e |
mapbox_list_styles | List custom map styles owned by your account |
FAQ
Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with Bearer headers.
Next steps
Was this guide helpful?