ChimeraForge for Windsurf

io.github.sahil170595/chimeraforge

Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance

client:Windsurf transport:stdio runtime:pypi

Install ChimeraForge in Windsurf

~/.codeium/windsurf/mcp_config.json · windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

{
  "mcpServers": {
    "chimeraforge": {
      "command": "uvx",
      "args": [
        "chimeraforge"
      ]
    }
  }
}

Global only — Windsurf has no per-project MCP config. Refresh Cascade after saving. Windsurf docs