vram_max_rank — MarvinLabs vram_fit MCP Tool
vram_max_rank
(vram max rank) is one of 3 tools on the
MarvinLabs vram_fit
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call vram_max_rank from your client
- Claude Code MarvinLabs vram_fit vram_max_rank run in your project directory
- Claude Desktop MarvinLabs vram_fit vram_max_rank ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor MarvinLabs vram_fit vram_max_rank ~/.cursor/mcp.json
- VS Code MarvinLabs vram_fit vram_max_rank .vscode/mcp.json
- Zed MarvinLabs vram_fit vram_max_rank ~/.config/zed/settings.json
- Windsurf MarvinLabs vram_fit vram_max_rank ~/.codeium/windsurf/mcp_config.json
- Cline MarvinLabs vram_fit vram_max_rank ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI MarvinLabs vram_fit vram_max_rank ~/.gemini/settings.json
- Grok MarvinLabs vram_fit vram_max_rank .mcp.json (in your project root)
- ChatGPT MarvinLabs vram_fit vram_max_rank Settings → Connectors → Advanced → Developer mode
- Claude.ai MarvinLabs vram_fit vram_max_rank Settings → Connectors → Add custom connector
- LangChain MarvinLabs vram_fit vram_max_rank pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http vram-fit https://marvinlabs.org/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 25 October 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.