Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Use this profile to copy client config, check auth requirements, review tools and resources, and compare related MCP servers before adding it to an AI client.
Get practical integration notes and launch examples for MCP servers like FitLLM.
https://fitllm.run/api/mcpAdd this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
{
"mcpServers": {
"run-fitllm-fitllm": {
"url": "https://fitllm.run/api/mcp"
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonNo remote HTTP endpoint is advertised. Use the package or stdio setup shown in Install.
FitLLM is an MCP server for Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.. It supports HTTP transport.
Use the generated config in Install. It points your client at the advertised remote endpoint shown on this page.
Choose the Claude Desktop tab in Install, copy the config, and add it to Claude Desktop's MCP server settings. Endpoint: https://fitllm.run/api/mcp.
Choose the Claude Code tab in Install, copy the config, and add it to Claude Code's MCP server settings. Endpoint: https://fitllm.run/api/mcp.
Choose the Codex tab in Install, copy the config, and add it to Codex's MCP server settings. Endpoint: https://fitllm.run/api/mcp.
Choose the Cursor or VS Code tab in Install, copy the config, and add it to Cursor or VS Code's MCP server settings. Endpoint: https://fitllm.run/api/mcp.
FitLLM uses HTTP transport. Endpoint: https://fitllm.run/api/mcp.
FitLLM inventory is listed when the MCP endpoint exposes tools, resources, or prompts. Some servers require auth first.
FitLLM does not advertise a verified auth requirement. If discovery fails, it may still need provider login, an API key, a bearer token, or a session header.