tt-mcp

samgutentag/tt-mcp
★ 0 stars Python 🤖 AI/LLM Updated 1d ago
MCP server that wraps Tenstorrent inference endpoints so AI agents can call accelerator hardware as a first-class tool
View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "tt-mcp": {
      "command": "uvx",
      "args": [
        "tt-mcp"
      ]
    }
  }
}

Or install with pip: pip install tt-mcp

README Excerpt

An MCP (Model Context Protocol) server that wraps Tenstorrent inference endpoints, so any MCP-compatible agent (Claude Desktop, the MCP Inspector, an IDE plugin) can call Tenstorrent hardware as a first-class tool. Works against a local Ollama install for development, then flips to a hosted Tenstorrent

Tools (7)

TT_API_KEYTT_ENDPOINTTT_HARDWARETT_MODELgeneratehardware_infolist_models