What is Pumperly Mcp?
It is a small server that acts as a bridge between any Pumperly instance and the Model Context Protocol, allowing LLMs to query fuel‑price data through standard MCP resources and tools.
@GeiserX
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"pumperly": {
"command": "npx",
"args": [
"-y",
"pumperly-mcp"
],
"env": {
"PUMPERLY_URL": "https://pumperly.com"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Pumperly Mcp is a bridge that exposes any Pumperly instance as an MCP server, enabling large language models to query real‑time fuel prices, find stations, plan routes, and geocode locations. It is intended for developers and LLM agents who need to integrate fuel‑price data into their workflows.
Install via Docker Compose (drumsergio/pumperly-mcp:latest), via npm (npx pumperly-mcp or global install), or by building from source with Go. Configure the Pumperly instance URL with the PUMPERLY_URL environment variable, choose transport (HTTP on port 8080 by default or stdio), and then use MCP tools to interact.
pumperly://config, pumperly://stats, pumperly://exchange‑rates)find_nearest_stations, get_stations_in_area, calculate_route, find_route_stations, geocode/mcpIt is a small server that acts as a bridge between any Pumperly instance and the Model Context Protocol, allowing LLMs to query fuel‑price data through standard MCP resources and tools.
You can run it via Docker Compose with the image `drumsergio/pumperly-mcp:latest`, install it globally with npm (`npm install -g pumperly-mcp`), or build it locally from the GitHub repository.
It supports HTTP (default, listening on `127.0.0.1:8080`) and stdio (set the `TRANSPORT` environment variable to `stdio`).
No, authentication is set to `none`. The HTTP transport listens on localhost by default; if exposed to a network, it should be placed behind a reverse proxy with authentication.
You can read configuration, statistics, and exchange rates via its resources, and call tools to find nearby stations, get stations in an area, calculate routes, find stations along a route, and geocode locations.
Open-source MCP to use Blender with any LLM
不止于 CSS

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
🚀 The fast, Pythonic way to build MCP servers and clients.
评论