About CS2 RCON MCP
CS2 RCON MCP is an MCP server for managing and monitoring Counter-Strike 2 servers through RCON. It exposes command execution, status checks, and workshop map controls, with SSE communication and Docker support.
Key features
- 01Execute RCON commands
- 02Check current server status
- 03List workshop maps
- 04Host and change workshop maps
- 05Communicate over SSE
Use cases
- 01Check server status and connected players
- 02Run administrative RCON commands
- 03Host or switch to a workshop map
MCP support
Exposes RCON and workshop-map management tools to MCP clients, including status checks and map listing, hosting, and switching.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMECS2 RCON MCP
A Model Context Protocol server for CS2 RCON management.
Description
This project provides a Model Context Protocol (MCP) server interface for managing CS2 game servers via RCON. It allows remote control and monitoring of CS2 servers through a standardized protocol.

Features
- Manage your CS2 server in natural language
- RCON command execution
- Manage workshop maps (host, list, change) - Explore Workshop Maps
- SSE-based communication
- Docker support
Available Tools
| Tool | Short Description |
|---|---|
rcon | Execute any RCON command |
status | Get current server status |
list_workshop_maps | List all workshop maps on the server |
host_workshop_map | Host a workshop map by its ID |
workshop_changelevel | Change the map to a given workshop map |
Installation
Environment Variables
HOST: CS2 server IPSERVER_PORT: CS2 server portRCON_PASSWORD: RCON password
Docker (recommended)
Pull the Docker image from GitHub Container Registry:
docker pull ghcr.io/v9rt3x/cs2-rcon-mcp:latest
Docker Environment Variables
When running with Docker, you can set the environment variables in two ways:
-
Directly in the command:
docker run -p 8080:8080 \ -e HOST=your_server_ip \ -e SERVER_PORT=your_server_port \ -e RCON_PASSWORD=your_password \ ghcr.io/v9rt3x/cs2-rcon-mcp:latest -
Using a
.server-envfile: Create a file named.server-envwith the following content:HOST=your_server_ip SERVER_PORT=your_server_port RCON_PASSWORD=your_passwordThen run the container like this:
docker run -p 8080:8080 --env-file .server-env ghcr.io/v9rt3x/cs2-rcon-mcp:latest
This provides users with an alternative method to set environment variables, making it easier to manage sensitive information like passwords.
Connecting from Visual Studio Code (GitHub Copilot)
To configure Visual Studio Code to work with the MCP server, follow these steps:
-
Start the MCP Server: Ensure that your MCP server is running before attempting to connect from VS Code.
-
Open Visual Studio Code: Launch VS Code and ensure that you have the GitHub Copilot extension installed and configured.
-
Configure GitHub Copilot:
- Change the mode from "Ask" to "Agent" mode.
-
Add MCP Server Configuration:
- Click on the toolbox icon in the upper left corner of the Copilot prompt.
- Select "Add MCP Server" and choose the option for HTTP - server-sent events.
-
Enter the Server URL:
- For the URL, input:
http://localhost:8080/cs2server/sse. This is the endpoint for the MCP server's SSE connection.
- For the URL, input:
Alternative: Connecting from Cursor (or any other MCP-Client)
- Start the MCP server
- Configure Cursor's MCP settings by creating or updating
~/.cursor/mcp.json:{ "mcpServers": { "cs2server": { "url": "http://localhost:8080/cs2server/sse" } } } - In Cursor, open the MCP panel (usually in the sidebar)
- The server should automatically connect using the configured URL
Once connected, you can manage your server in natural language.
Example prompts:
- "Add 5 bots to the server and start a competitive match on de_dust2"
- "What's the current server status? How many players are connected and what map are we on?"
Happy fragging! 😊
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.