Venice

Model Context Protocol (MCP) server for Venice AI - Chat, Image Generation, TTS, Embeddings & Admin tools
  • typescript

3

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "georgeglarson-venice-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "venice-mcp"
      ],
      "env": {
        "VENICE_API_KEY": "YOUR_VENICE_API_KEY"
      }
    }
  }
}

A Venice MCP Server lets you connect Claude or other MCP‑compatible assistants to Venice AI’s capabilities. It unlocks chat with various language models, image generation, text-to-speech, embeddings, and account management APIs, enabling seamless AI-assisted workflows through a single MCP endpoint.

How to use

You use the Venice MCP Server by running it as a local process or deploy it as an MCP endpoint that your MCP client can call. Once running, your MCP client can access Venice features for chat, image generation, TTS, embeddings, and API key management. You’ll interact through the MCP tools provided by your client, selecting the Venice tools to perform each action.

How to install

Prerequisites: you need Node.js 18+ installed on your machine.

Step by step follow these commands to install and run the Venice MCP Server locally.

# Install the MCP server globally
npm install -g venice-mcp

Configuration and usage notes

You configure the Venice MCP Server to provide a secure connection for your MCP client and supply your Venice API key. The standard approach is to run the server as a stdio process using npx, with the Venice API key supplied via an environment variable.

{
  "mcpServers": {
    "venice": {
      "command": "npx",
      "args": ["-y", "venice-mcp"],
      "env": {
        "VENICE_API_KEY": "YOUR_VENICE_API_KEY"
      }
    }
  }
}

Start and use from Claude Desktop

Add Venice MCP as a server in Claude Desktop using the provided config path for your platform. After you restart Claude Desktop, Venice tools appear in the tooling menu and you can start issuing commands to Venice via the MCP bridge.

Examples of typical usage patterns

  • Start a chat with Venice models to get responses from Llama, DeepSeek, or Qwen-based systems.

  • Generate an image from a text prompt and then upscale or refine it.

  • Create text embeddings for a search or RAG workflow and retrieve similar content.

Available tools

venice_chat

Chat with Venice AI language models such as Llama, DeepSeek, and Qwen.

venice_generate_image

Generate images from text descriptions using Venice's image models.

venice_upscale_image

Upscale and enhance generated images to higher resolution.

venice_text_to_speech

Convert text to natural-sounding speech.

venice_create_embeddings

Generate text embeddings for search and retrieval tasks.

venice_list_models

List available language, image, and embedding models.

venice_list_characters

List character personas or agent profiles.

venice_list_api_keys

List all API keys managed by Venice MCP.

venice_create_api_key

Create a new API key for Venice MCP usage.

venice_retrieve_api_key

Get details for a specific API key.

venice_delete_api_key

Delete an API key.

venice_get_rate_limits

View current rate limits and usage.

venice_get_rate_limit_logs

View history of rate limit events.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational