Pumperly

Query real-time fuel prices, find nearby stations, plan routes, and geocode locations across different countries

Install

Install and configure the MCP from https://github.com/GeiserX/pumperly-mcp now. Follow the repository's installation instructions, ask me for anything you can't complete yourself, and verify its tools load.

View source on GitHub

README

pumperly-mcp

A small bridge that exposes any Pumperly instance as an MCP server, so an AI agent can query fuel prices, find stations, plan routes and geocode places.

Features

Five tools: find_nearest_stations, get_stations_in_area, calculate_route, find_route_stations, geocode.
Three read-only resources: pumperly://config, pumperly://stats, pumperly://exchange-rates.
Two transports: stdio, and HTTP on a single /mcp endpoint.
An npm package that downloads the release binary for your platform and runs it over stdio.
A Docker image for amd64 and arm64.
Works with the public instance at pumperly.com or your own: set PUMPERLY_URL.
No API key: it reads the Pumperly API anonymously.

Quick start

Add this to your MCP client's configuration (Claude Desktop, Claude Code, Cursor and others read the mcpServers format):

{
  "mcpServers": {
    "pumperly": {
      "command": "npx",
      "args": ["-y", "pumperly-mcp"],
      "env": { "PUMPERLY_URL": "https://pumperly.com" }
    }
  }
}

For the HTTP transport (/mcp on port 8080) run the Docker image; see Getting started.

Documentation

Getting started: npm, Docker Compose, building from source, connecting a client
Configuration: environment variables
Usage: tools, resources, the request flow, testing with the Inspector
Related projects: the Pumperly family, other MCP servers, registry listings

License

GPL-3.0-or-later