Venice MCP Server
Officialby veniceai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP-mode listener port. | 3333 |
| VENICE_API_KEY | No | Your Venice API key. The simplest setup. | |
| VENICE_MCP_HOST | No | HTTP-mode bind address. Set to 0.0.0.0 for LAN/container exposure. | 127.0.0.1 |
| VENICE_SIWX_TOKEN | No | Base64 SIWE payload for x402 wallet-mode authentication. | |
| VENICE_DISABLE_NSFW | No | Set to '1' to remove NSFW capability notes from tool descriptions. | 0 |
| VENICE_MCP_AUTH_TOKEN | No | Bearer token required by /mcp whenever HTTP mode binds outside loopback. | |
| VENICE_HTTP_TIMEOUT_MS | No | HTTP timeout in milliseconds. | 60000 |
| VENICE_MCP_MAX_SESSIONS | No | Maximum active Streamable HTTP sessions. | 100 |
| VENICE_DEFAULT_ASR_MODEL | No | Default ASR model. | openai/whisper-large-v3 |
| VENICE_DEFAULT_TTS_MODEL | No | Default TTS model. | tts-kokoro |
| VENICE_DEFAULT_CHAT_MODEL | No | Default chat model. | venice-uncensored |
| VENICE_MCP_SESSION_TTL_MS | No | Idle Streamable HTTP session lifetime before cleanup. | 1800000 |
| VENICE_DEFAULT_IMAGE_MODEL | No | Default image model. | flux-2-pro |
| VENICE_MCP_ALLOW_UNAUTHENTICATED_HTTP | No | Emergency escape hatch for unauthenticated exposed HTTP mode. | 0 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/veniceai/venice-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server