OPET Fuel Prices MCP Server
Provides access to OPET fuel station prices across Turkish provinces. Enables querying fuel prices by province, listing available provinces, and checking last update timestamps.
README
OPET Fuel Prices MCP Server
A Model Context Protocol (MCP) server that provides access to OPET fuel prices data through Claude AI.
Demo

Features
- Get all available provinces
- Fetch fuel prices for specific provinces
- Get last update timestamp
- Error handling with detailed messages
Prerequisites
Before using this MCP server, you need to set up the OPET API server first.
1. Install OPET Package
Install the OPET package from https://github.com/sinanerdinc/opet:
pip install opet
2. Start OPET API Server
Start the API server using one of the following methods:
Option A: Using CLI
opet-cli --api
Option B: Using Docker
docker run -p 8000:8000 sinanerdinc/opet api
Option C: Using Docker with custom port
docker run -p 5050:8000 sinanerdinc/opet api
The API server will be available at http://localhost:8000 (or your custom port).
Installation
Prerequisites
- Python 3.12 or higher
- uv package manager (recommended) or pip
- OPET package installed and API server running
Setup
- Clone the repository:
git clone <repository-url>
cd opet-mcp
- Using uv
# Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create virtual environment and install dependencies
uv venv -p 3.12
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv sync
Configuration
Set the OPET API URL using environment variables. The URL should point to your running OPET API server:
# If using default port (8000)
export OPET_API_URL=http://localhost:8000
# If using custom port (e.g., 5050)
export OPET_API_URL=http://localhost:5050
Usage
Running the Server
Start the MCP server:
# With uv
uv run fastmcp run server.py
# With pip
fastmcp run server.py
Example Configuration
Option 1: Install the server to Claude with a custom name and API URL:
{
"mcpServers": {
"Opet Server": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"fastmcp",
"run",
"/your_absolute_path/opet-mcp/server.py"
],
"env": {
"OPET_API_URL": "http://localhost:8000"
}
}
}
}
Option 2: Installation Command
fastmcp install server.py --name "OPET Fuel Prices" \
--env-var OPET_API_URL=http://localhost:8000
Available Tools
get_all_provinces()
Retrieves a list of all provinces where fuel prices are available.
get_fuel_prices_by_province(province_id)
Fetches current fuel prices for a specific province using its ID.
Parameters:
province_id(str): The unique identifier of the province
get_last_update_time()
Gets the timestamp of when the fuel prices were last updated in the system.
License
This project is licensed under the MIT License - see the LICENSE file for details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。