gdebenz
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@gdebenzКакая ближайшая заправка Лукойл с дизелем, и есть ли там очередь?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
gdebenz-mcp
MCP server for finding gasoline and diesel at Russian gas stations. Combines two independent sources — gdebenz.ru and gdebenzi.ru — crowdsourced fuel availability maps with real-time driver check-ins.
Lets your AI assistant (Claude, Cursor, OpenClaw, etc.) answer questions like:
"Where near Khimki is there 95-octane gasoline?" "What's the nearest Lukoil station with diesel, and is there a queue?"
Works through the public APIs of both services. No API keys needed — just Python and two packages.
Two data sources
Source | What it provides |
| availability status, fuel list, confirmations, freshness ( |
| status, queue text ("queue of 25–50 cars"), limits (L), confirmed fuel ( |
The search tools have a source parameter: "gdebenz", "gdebenzi", or "both" (default is both — maximum coverage).
Installation
1. Clone the repository
git clone https://github.com/ivanegorenkov/gdebenz-mcp.git
cd gdebenz-mcp2. Install dependencies
pip install -r requirements.txtRequires Python 3.10+.
3. Connect the server to your assistant
Claude Desktop — open/create claude_desktop_config.json:
{
"mcpServers": {
"gdebenz": {
"command": "python3",
"args": ["/АБСОЛЮТНЫЙ/ПУТЬ/gdebenz-mcp/server.py"]
}
}
}Cursor — in the project's .cursor/mcp.json (or global ~/.cursor/mcp.json):
{
"mcpServers": {
"gdebenz": {
"command": "python3",
"args": ["/АБСОЛЮТНЫЙ/ПУТЬ/gdebenz-mcp/server.py"]
}
}
}OpenClaw:
openclaw mcp add gdebenz --command python3 --arg /АБСОЛЮТНЫЙ/ПУТЬ/gdebenz-mcp/server.py⚠️ Replace
/ABSOLUTE/PATH/with the actual path where the repository was cloned (you can find it by runningpwdinside the folder).
Related MCP server: opinet-mcp
Instructions for the AI agent
If the user asks to "set up this MCP server" — do the following:
git clone https://github.com/ivanegorenkov/gdebenz-mcp.gitcd gdebenz-mcp && pip install -r requirements.txtDetermine the user's MCP host (Claude Desktop / Cursor / OpenClaw) and add the
gdebenzentry to its config, as shown above (with the absolute path toserver.py).Restart the host/application.
Verify the server is visible (in OpenClaw:
openclaw mcp probe gdebenz).
The server is stdio-based and requires no external keys.
What it can do (9 tools)
Tool | What it does |
| Main one. Stations with fuel near a location (by name or coordinates). Filters: fuel, brand, status, radius, |
| Stations around a point (lat/lon + radius + |
| Stations in an area + prices (bbox + |
| Search for a station by name/address. |
| Place name → coordinates. |
| My location by IP. |
| City by coordinates. |
| Fuel grades: 92 / 95 / 98 / 100 / diesel. |
| Common gas station chains (the filter accepts any string). |
Example request to the assistant: find_fuel(location="Khimki", fuel="95", brand="Lukoil", source="both").
Semantics
Fuel:
92, 95, 98, 100, diesel. For gdebenz —fuels_now(comma-separated string), for gdebenzi —fuels_yes/fuels_no/fuels_maybe(arrays with Russian names, e.g.["АИ-95", "ДТ"]).Status:
yes— available,queue— available/queue,low— low,no— unavailable,unknown— unknown,changing— updating,dtonly— diesel only.Freshness: for gdebenz —
last_at,confirmations,confidence(0..1); for gdebenzi —last_mark(check-in time),confidence_pct,marks,reports. Both sources returnage_minutesandfreshness("just now", "3 h ago").Queue/limits (gdebenzi):
queue("queue of 25–50 cars"),limits(limit in liters per fuel grade).Prices: gdebenz —
prices_now[fuel].t(price report time); gdebenzi —prices(keysai92/ai95/ai98/ai100/dt/gas) andregional_prices(regional averages).
API (where the data comes from)
gdebenz.ru
Endpoint | Purpose |
| stations around a point |
| stations in bbox + prices |
| text search |
| geocoding |
| location by IP |
| city by coordinates |
gdebenzi.ru
Endpoint | Purpose |
| stations in bbox (status, queue, limits, prices, check-ins) |
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables location-aware AI agents to search for nearby places, get detailed place information including hours and ratings, and calculate routes with turn-by-turn directions using Google Maps APIs.21
- AlicenseAqualityDmaintenanceProvides access to Korea Petroleum Corporation's Opinet fuel price API for South Korea. Enables querying of current national and regional fuel averages, recent price trends, lowest-price stations, and nearby gas station details through natural language.MIT
- AlicenseNot gradedqualityDmaintenanceEnables querying global EV charging station data from Open Charge Map through natural language, accessing real-time station information via the Pipeworx gateway.8MIT
- FlicenseAqualityDmaintenanceProvides map services such as geocoding, POI search, and route planning through the Amap API, enabling AI applications to interact with map data via natural language.12
Related MCP Connectors
Live Google Maps business search, review, and photo data for AI agents over MCP.
Find EV charging stations, detail, and reliability check-ins via the global Open Charge Map.
Vanlife & RV travel data. Fuel, weather, currency, events, news. https://openvan.camp/en/developers
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ivanegorenkov/gdebenz-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server