Venice
Venice AI MCP Server for Claude Code, Cline, and AI agents
What is Venice?
Venice is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to venice ai mcp server for claude code, cline, and ai agents
Venice AI MCP Server for Claude Code, Cline, and AI agents
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Venice AI MCP Server for Claude Code, Cline, and AI agents
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx veniceConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Venice
The Venice AI MCP server connects AI coding assistants and agent frameworks to Venice.ai's privacy-preserving AI platform, exposing 31 tools spanning text generation, image creation and editing, video generation, audio text-to-speech and transcription, music generation, web search and scraping, and blockchain JSON-RPC calls. Venice runs open-source models with no data retention, making it an alternative to OpenAI or Anthropic APIs for use cases requiring confidentiality. Install it in Claude Desktop, Cursor, or any MCP-compatible host with a single JSON config block and a Venice API key.
Prerequisites
- Node.js 18 or later with npx available
- A Venice.ai account and API key from venice.ai (or a SIWX wallet token for keyless crypto-wallet authentication)
- An MCP client such as Claude Desktop, Claude Code, Cursor, or LM Studio
- Optional: Docker for self-hosted deployment of the MCP server with shared access
Obtain a Venice API key
Sign up at venice.ai and generate an API key from your account settings. Alternatively, use wallet-based SIWX authentication with a Base mainnet USDC wallet — no email or KYC required for that path.
Add the MCP server to your client config
Open your MCP client configuration file (e.g., claude_desktop_config.json for Claude Desktop) and add the Venice server block with your API key.
{
"mcpServers": {
"venice": {
"command": "npx",
"args": ["-y", "@veniceai/[email protected]"],
"env": {
"VENICE_API_KEY": "<your-venice-api-key>"
}
}
}
}Optionally configure default model overrides
Set environment variables to change the default models used for chat, image, and TTS operations. If not set, defaults are venice-uncensored (chat), flux-2-pro (image), and tts-kokoro (TTS).
"env": {
"VENICE_API_KEY": "<your-venice-api-key>",
"VENICE_DEFAULT_CHAT_MODEL": "llama-3.3-70b",
"VENICE_DEFAULT_IMAGE_MODEL": "flux-dev",
"VENICE_DEFAULT_TTS_MODEL": "tts-kokoro"
}Restart your MCP client
Save the config file and restart Claude Desktop (or your chosen MCP host) to load the Venice server. You should see Venice tools become available in the tool list.
Optional: self-host with Docker
For team deployments where multiple agents share one Venice MCP server, use the official Docker image with an auth token to secure the endpoint.
docker run -p 3333:3333 \
-e VENICE_API_KEY=<your-key> \
-e VENICE_MCP_AUTH_TOKEN=<shared-auth-token> \
ghcr.io/veniceai/venice-mcp-server:latestVenice Examples
Client configuration
Complete Claude Desktop configuration for the Venice MCP server using an API key.
{
"mcpServers": {
"venice": {
"command": "npx",
"args": ["-y", "@veniceai/[email protected]"],
"env": {
"VENICE_API_KEY": "<your-venice-api-key>",
"VENICE_DEFAULT_CHAT_MODEL": "venice-uncensored",
"VENICE_DEFAULT_IMAGE_MODEL": "flux-2-pro",
"VENICE_DEFAULT_TTS_MODEL": "tts-kokoro"
}
}
}
}Prompts to try
These prompts exercise the range of Venice's 31 tools across text, image, audio, video, and web capabilities.
- "Generate a photorealistic image of a mountain lake at sunset."
- "Transcribe this audio file and return the text."
- "Search the web for the latest news about quantum computing."
- "List all available Venice AI models."
- "Generate a 30-second music track in a jazz style."
- "Convert this paragraph to speech using the tts-kokoro voice."Troubleshooting Venice
Authentication error: VENICE_API_KEY is invalid or missing.
Confirm your API key is correctly copied from venice.ai and is set in the env block of your MCP config. The key should not contain extra whitespace. If using wallet-based auth, use VENICE_SIWX_TOKEN instead and leave VENICE_API_KEY unset.
npx fails to download @veniceai/mcp-server or installs an old version.
Pin to a specific version with @veniceai/[email protected] in your args array. If npx cache issues persist, clear it with 'npx clear-npx-cache' or install globally with 'npm install -g @veniceai/mcp-server'.
Image or video generation tools time out without returning results.
Video generation in particular is asynchronous. Use the video status tracking tool to poll for completion rather than waiting for a synchronous response. For image generation, try a lighter model (flux-dev instead of flux-2-pro) if latency is too high.
Frequently Asked Questions about Venice
What is Venice?
Venice is a Model Context Protocol (MCP) server that venice ai mcp server for claude code, cline, and ai agents It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Venice?
Follow the installation instructions on the Venice GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Venice?
Venice works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Venice free to use?
Yes, Venice is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Venice Alternatives — Similar Coding Agents Servers
Looking for alternatives to Venice? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Venice in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Venice?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.