The ref-tools-mcp server provides AI agents with tools to integrate and manage machine learning models. It exposes functionality to load, train, and evaluate models, and connects to popular ML frameworks like TensorFlow and PyTorch. Developers use it to build AI applications that require model inference, fine-tuning, and deployment.
The ref-tools-mcp server provides AI agents with tools to integrate and manage machine learning models. It exposes functionality to load, train, and evaluate models, and connects to popular ML frameworks like TensorFlow and PyTorch. Developers use it to build AI applications that require model inference, fine-tuning, and deployment.
npx -y ref-tools-mcpAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"ref-tools-mcp-npm": {
"command": "npx",
"args": [
"-y",
"npx -y ref-tools-mcp"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from ref-tools-mcp?"
No configuration required. This server works out of the box.
"What resources are available in ref-tools-mcp?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in ref-tools-mcp"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in ref-tools-mcp with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.