Shaderc-VkRunner (GPU Shader Sandbox) MCP server

This Rust-based tool provides a secure sandbox for AI agents to develop, compile, optimize, and run GPU shaders using Vulkan without physical GPU hardware. It operates entirely locally through Docker, creating a safe execution environment for experimenting with shader code.

Installation

The MCP server comes packaged as a Docker image with all necessary dependencies included. Docker is the only requirement to use this tool.

Building from Source

git clone https://github.com/mehmetoguzderin/shaderc-vkrunner-mcp
cd shaderc-vkrunner-mcp
docker build -t shaderc-vkrunner-mcp -f Dockerfile .

Connecting to MCP Clients

VS Code Copilot

To use with VS Code Copilot, add this configuration to your mcp.json file:

"shaderc-vkrunner-mcp": {
    "type": "stdio",
    "command": "docker",
    "args": [
        "run",
        "--rm",
        "-i",
        "-v", "${workspaceFolder}:/work",
        "shaderc-vkrunner-mcp",
        "--work-dir",
        "/work"
    ]
}

You can then reference it in your Copilot Chat using the #compile_run_shaders tag in Agent mode.

MCP Inspector

For debugging and testing purposes, you can use the MCP Inspector:

npx @modelcontextprotocol/inspector docker run -i --rm shaderc-vkrunner-mcp

Features and Capabilities

The MCP server offers several key features:

• Safe Execution: Uses Mesa's software Vulkan implementation to run shaders on CPU
• Local Operation: Works entirely locally with no additional API dependencies
• Comprehensive Support: Handles shader compilation, optimization, and visualization
• Advanced Features: Supports subgroup operations, atomic operations, and more
• Cross-platform: Uses Vulkan instead of CUDA/OpenCL for broader compatibility

All of these features run safely on CPU, eliminating the risk of GPU crashes or lost devices that typically create barriers for GPU programming experimentation.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.