# GeiserX/pumperly-mcp [Health: Active]

**Category:** 🚆 Travel & Transportation  
**Repository:** https://github.com/GeiserX/pumperly-mcp  
**GitHub Stars:** 3  
**npm Downloads (last month):** 256  
**Views:** 4  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/geiserx-pumperly-mcp

## Description
Go-based MCP server for Pumperly fuel price comparison. Query gas station prices, plan fuel-efficient routes, and find nearby EV charging stations. Docker image available.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "pumperly-mcp": {
    "command": "npx",
    "args": ["-y","pumperly-mcp"],
    "env": {
      "PUMPERLY_URL": ""
    }
  }
}
```

**Requires environment variables:** `PUMPERLY_URL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What GeiserX/pumperly-mcp does

GeiserX/pumperly-mcp acts as an MCP bridge for Pumperly. It lets an MCP-compatible agent query fuel information without integrating with Pumperly directly. The server can search for nearby stations, list stations within an area, calculate routes, identify stations along a route, and convert place names into geographic coordinates.

It can connect to the public Pumperly service at pumperly.com or to another Pumperly deployment. Pumperly’s API is accessed anonymously, so the setup does not require an API key.

## How it works

The server offers five callable tools:

- `find_nearest_stations` searches for nearby fuel stations.
- `get_stations_in_area` returns stations for a specified area.
- `calculate_route` plans a route.
- `find_route_stations` locates stations associated with a route.
- `geocode` resolves places into geographic data.

Three read-only MCP resources provide access to `pumperly://config`, `pumperly://stats`, and `pumperly://exchange-rates`. These resources are useful for retrieving service configuration, usage or service statistics, and currency exchange-rate data without mutating the connected Pumperly instance.

Two transport modes are available. Stdio is suited to desktop and local agent configurations. HTTP exposes the MCP service through a single `/mcp` endpoint; the Docker usage example runs that endpoint on port 8080.

## Setup and configuration

For a local stdio setup, configure an MCP client to launch the npm package with `npx`:

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

Set `PUMPERLY_URL` to the Pumperly instance the server should use. The npm package downloads and runs a release binary for the local platform. Docker images are available for amd64 and arm64 and provide the HTTP deployment path. The project also documents Docker Compose and building from source as setup options.

## Tools and capabilities

The server is intended for travel and transportation workflows involving fuel prices and station discovery. Agents can compare station availability near a location, inspect stations within an area, plan fuel-related routes, and use geocoding as part of location-based requests. The connected Pumperly data can also support finding nearby EV charging stations.

## Limitations and notes

The server reads Pumperly anonymously and does not use an API key. Its data depends on the selected Pumperly instance, whether that is the public service or a custom deployment. Resource access is read-only, and the HTTP transport uses the `/mcp` path rather than multiple service endpoints. Client configuration must support the MCP `mcpServers` format for the stdio example.

_Full upstream README: https://allmcps.com/mcp/geiserx-pumperly-mcp/readme_