Venice MCP Server

A Model Context Protocol (MCP) server for Venice AI. Gives AI assistants like Claude access to Venice's text generation, image creation, text-to-speech, embeddings, and account management APIs.

What It Does

This MCP server lets Claude (or any MCP-compatible assistant) use Venice AI's features directly:

• Chat with Llama, DeepSeek, Qwen, and other open models
• Generate images using Stable Diffusion, FLUX, and more
• Create speech from text with natural-sounding voices
• Generate embeddings for search and RAG applications
• Manage API keys and monitor rate limits

Quick Start

1. Get a Venice API Key

Sign up at venice.ai and create an API key in Settings API.

2. Install

npm install -g venice-mcp

3. Configure Claude Desktop

Add to your config file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "venice": {
      "command": "npx",
      "args": ["-y", "venice-mcp"],
      "env": {
        "VENICE_API_KEY": "your-api-key-here"
      }
    }
  }
}

Restart Claude Desktop. You'll see Venice tools available in the menu.

Available Tools

Generation

Discovery

Account Management

Requires an admin-level API key:

Examples

Ask Claude to generate an image:

"Use Venice to create an image of a sunset over mountains"

Chat with a specific model:

"Ask Venice's DeepSeek model to explain quantum computing"

Check your usage:

"Show my Venice API rate limits"

Supported Models

Language Models: Llama 3.3 70B, DeepSeek R1, Qwen 3, Mistral, and more
Image Models: Stable Diffusion 3.5, FLUX, Fluently XL
Embeddings: BGE-M3 (1024 dimensions)
TTS: Kokoro with multiple voice options

Run venice_list_models to see all currently available models.

Requirements

• Node.js 18+
• Venice AI API key

Links

• Venice AI - Platform home
• Venice API Docs - API reference
• MCP Documentation - Protocol spec

License

MIT - see LICENSE