Vox MCP server

Vox MCP

Multi-model AI gateway for MCP clients.

Why

MCP clients like Claude Code, Claude Desktop, and Cursor are locked to their host model. Vox gives them access to every other model — Gemini, GPT, Grok, DeepSeek, Kimi, or your local Ollama — through a single chat tool.

The design is deliberately minimal: prompts go to providers unmodified, responses come back unmodified. No system prompt injection. No response formatting. No behavioral directives. The only value Vox adds is routing and conversation memory — everything else is pure passthrough.

What it does

Send a prompt, optionally attach files or images, pick a model (or let the agent pick), and get back the model's raw response. Conversation threads persist in memory via continuation_id for multi-turn exchanges across any provider — start a thread with Gemini, continue it with GPT. Threads are shadow-persisted to disk as JSONL for durability and can be exported as Markdown.

3 tools:

8 providers:

Quick start

git clone https://github.com/linxule/vox-mcp.git
cd vox-mcp
cp .env.example .env
# Edit .env — add at least one API key
uv sync
uv run python server.py

MCP client configuration

Vox runs as a stdio MCP server. Each client needs to know how to launch it.

Replace /path/to/vox-mcp with the absolute path to your cloned repo.

Claude Code (CLI)

claude mcp add vox-mcp \
  -e GEMINI_API_KEY=your-key-here \
  -- uv run --directory /path/to/vox-mcp python server.py

Or add to .mcp.json in your project root:

{
  "mcpServers": {
    "vox-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/vox-mcp", "python", "server.py"],
      "env": {
        "GEMINI_API_KEY": "your-key-here"
      }
    }
  }
}

Claude Desktop

Add to claudedesktopconfig.json:

macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json Windows: %APPDATA%\Claude\claudedesktopconfig.json

{
  "mcpServers": {
    "vox-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/vox-mcp", "python", "server.py"],
      "env": {
        "GEMINI_API_KEY": "your-key-here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "vox-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/vox-mcp", "python", "server.py"],
      "env": {
        "GEMINI_API_KEY": "your-key-here"
      }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "vox-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/vox-mcp", "python", "server.py"],
      "env": {
        "GEMINI_API_KEY": "your-key-here"
      }
    }
  }
}

Any MCP client

The canonical stdio configuration:

{
  "mcpServers": {
    "vox-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/vox-mcp", "python", "server.py"],
      "env": {
        "GEMINI_API_KEY": "your-key-here"
      }
    }
  }
}

Shortened. The full README is on GitHub.