ChimeraForge

Overview

ChimeraForge is a local-first LLM deployment planner that helps you size GPU and VRAM requirements, estimate costs, and predict latency for language model inference. It speaks the Model Context Protocol, so AI assistants can call its tools directly instead of requiring manual data transfer between applications.

The server runs entirely on your machine via the Python package chimeraforge, installed with uvx chimeraforge. It communicates over stdio and requires no authentication or external credentials to get started. It is published under the MIT license at version v0.30.9, with source code available at Sahil170595/Chimeraforge on GitHub.

ChimeraForge appears in the AI & Agents category on mcp.site and works with any MCP client, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim your listing to earn the Verified badge and keep its information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "chimeraforge": {
      "command": "uvx",
      "args": [
        "chimeraforge"
      ]
    }
  }
}