shaderc-vkrunner-mcp vs filesystem
Side-by-side comparison to help you pick between these two MCP servers.
shaderc-vkrunner-mcp by mehmetoguzderin | filesystem by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 6 | ★ 85,748 |
| 30d uses | — | — |
| Score | 34 | 77 |
| Official | — | ✓ |
| Categories | Developer ToolsAI / LLM ToolsOther | File SystemDeveloper ToolsProductivity |
| Language | C++ | TypeScript |
| Last commit | 9 mo ago | this month |
shaderc-vkrunner-mcp · Summary
A toy MCP server for AI agents to safely code, compile, and run GPU shaders using Vulkan via CPU emulation.
filesystem · Summary
A feature-rich MCP server for filesystem operations with dynamic directory access control.
shaderc-vkrunner-mcp · Use cases
- AI-assisted shader development and optimization
- Vulkan shader education and experimentation
- Testing shader features without physical GPU hardware
filesystem · Use cases
- Enable AI models to read and write project files during development
- Allow Claude or other MCP clients to browse and analyze codebases
- Provide secure sandboxed access to specific directories for content generation
shaderc-vkrunner-mcp · Install
Installation
- Clone the repository:
git clone https://github.com/mehmetoguzderin/shaderc-vkrunner-mcp
cd shaderc-vkrunner-mcp- Build the Docker image:
docker build -t shaderc-vkrunner-mcp -f Dockerfile .VS Code Integration
Add this to your VS Code mcp.json:
"shaderc-vkrunner-mcp": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v", "${workspaceFolder}:/work",
"shaderc-vkrunner-mcp",
"--work-dir",
"/work"
]
}filesystem · Install
Installation
Using NPX
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/path/to/allowed/directory"
]
}
}
}Using Docker
{
"mcpServers": {
"filesystem": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
"mcp/filesystem",
"/projects"
]
}
}
}VS Code Extension
Click the installation buttons in the README to install directly in VS Code.