Skip to main content
Glama
Venice MCP Server

Venice MCP Server

Official
by veniceai

Venice Chat (LLM)

venice_chat

Generate chat completions from Venice AI models using an OpenAI-compatible interface. Supports multimodal inputs, web search, and uncensored prompts; authenticate with API key or x402 wallet.

Instructions

Run an OpenAI-compatible chat completion via Venice's text-model catalog. Calls are non-streaming plaintext. Completion text longer than 8000 characters is truncated and the result reports omitted_chars in structured content. Completion id and actual model, when returned upstream, are available in structured content. Responses marked X-Venice-TEE: true also include a JSON text block for venice_tee_signature. enable_e2ee is rejected: this server does not encrypt chat. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "messages": "<messages>"
    },
    "name": "venice_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
stopNo
modelNoModel id. Defaults to deepseek-v4-flash-0731.
toolsNo
top_pNo
messagesYesChat messages. Multimodal image, audio, video, and file blocks belong in user messages.
reasoningNo
verbosityNoHow much text the model returns.
max_tokensNo
timeout_msNoUpstream timeout for this call, covering the full response body. Long generations may need more than the VENICE_HTTP_TIMEOUT_MS default.
temperatureNo
tool_choiceNo
response_formatNo
prompt_cache_keyNo
reasoning_effortNoTakes precedence over reasoning.effort.
venice_parametersNoVenice-only options: web search, citations, system prompt control, reasoning control, and characters.
parallel_tool_callsNo
max_completion_tokensNoMaximum visible plus reasoning tokens. Preferred over deprecated max_tokens.
prompt_cache_retentionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed23 schema fields changedv0.3.0
    • addedInput schema / properties / max_completion_tokens
      Added value: +{
      +  "description": "Maximum visible plus reasoning tokens. Preferred over deprecated max_tokens.",
      +  "exclusiveMinimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / messages / description
      Previous value: -"Chat messages, OpenAI format."New value: +"Chat messages. Multimodal image, audio, video, and file blocks belong in user messages."
    • removedInput schema / properties / messages / items / additionalProperties
      Removed value: -false
    • addedInput schema / properties / messages / items / anyOf
      Added value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "content": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "items": {
      +              "anyOf": [
      +                {
      +                  "additionalProperties": false,
      +                  "properties": {
      +                    "cache_control": {
      +                      "additionalProperties": false,
      +                      "description": "Prompt cache control for providers that support it.",
      +                      "properties": {
      +                        "ttl": {
      +                          "description": "Optional extended cache TTL, for example \"1h\".",
      +                          "type": "string"
      +                        },
      +                        "type": {
      +                          "const": "ephemeral",
      +                          "type": "string"
      +                        }
      +                      },
      +                      "required": [
      +                        "type"
      +                      ],
      +                      "type": "object"
      +                    },
      +                    "text": {
      +                      "minLength": 1,
      +                      "type": "string"
      +                    },
      +                    "type": {
      +                      "const": "text",
      +                      "type": "string"
      +                    }
      +                  },
      +                  "required": [
      +                    "type",
      +                    "text"
      +                  ],
      +                  "type": "object"
      +                },
      +                {
      +                  "additionalProperties": false,
      +                  "properties": {
      +                    "cache_control": {
      +                      "$ref": "#/properties/messages/items/anyOf/0/properties/content/anyOf/1/items/anyOf/0/properties/cache_control",
      +                      "description": "Prompt cache control for providers that support it."
      +                    },
      +                    "image_url": {
      +                      "additionalProperties": false,
      +                      "properties": {
      +                        "url": {
      +                          "description": "Public URL or base64 data URL for an image at least 64px square.",
      +                          "minLength": 1,
      +                          "type": "string"
      +                        }
      +                      },
      +                      "required": [
      +                        "url"
      +                      ],
      +                      "type": "object"
      +                    },
      +                    "type": {
      +                      "const": "image_url",
      +                      "type": "string"
      +                    }
      +                  },
      +                  "required": [
      +                    "type",
      +                    "image_url"
      +                  ],
      +                  "type": "object"
      +                },
      +                {
      +                  "additionalProperties": false,
      +                  "properties": {
      +                    "cache_control": {
      +                      "$ref": "#/properties/messages/items/anyOf/0/properties/content/anyOf/1/items/anyOf/0/properties/cache_control",
      +                      "description": "Prompt cache control for providers that support it."
      +                    },
      +                    "input_audio": {
      +                      "additionalProperties": false,
      +                      "properties": {
      +                        "data": {
      +                          "description": "Base64-encoded audio bytes; direct audio URLs are not supported.",
      +                          "minLength": 1,
      +                          "type": "string"
      +                        },
      +                        "format": {
      +                          "enum": [
      +                            "wav",
      +                            "mp3",
      +                            "aiff",
      +                            "aac",
      +                            "ogg",
      +                            "flac",
      +                            "m4a",
      +                            "pcm16",
      +                            "pcm24"
      +                          ],
      +                          "type": "string"
      +                        }
      +                      },
      +                      "required": [
      +                        "data"
      +                      ],
      +                      "type": "object"
      +                    },
      +                    "type": {
      +                      "const": "input_audio",
      +                      "type": "string"
      +                    }
      +                  },
      +                  "required": [
      +                    "type",
      +                    "input_audio"
      +                  ],
      +                  "type": "object"
      +                },
      +                {
      +                  "additionalProperties": false,
      +                  "properties": {
      +                    "cache_control": {
      +                      "$ref": "#/properties/messages/items/anyOf/0/properties/content/anyOf/1/items/anyOf/0/properties/cache_control",
      +                      "description": "Prompt cache control for providers that support it."
      +                    },
      +                    "type": {
      +                      "const": "video_url",
      +                      "type": "string"
      +                    },
      +                    "video_url": {
      +                      "additionalProperties": false,
      +                      "properties": {
      +                        "url": {
      +                          "description": "Public video URL, supported YouTube URL, or base64 video data URL.",
      +                          "minLength": 1,
      +                          "type": "string"
      +                        }
      +                      },
      +                      "required": [
      +                        "url"
      +                      ],
      +                      "type": "object"
      +                    }
      +                  },
      +                  "required": [
      +                    "type",
      +                    "video_url"
      +                  ],
      +                  "type": "object"
      +                },
      +                {
      +                  "additionalProperties": false,
      +                  "properties": {
      +                    "cache_control": {
      +                      "$ref": "#/properties/messages/items/anyOf/0/properties/content/anyOf/1/items/anyOf/0/properties/cache_control",
      +                      "description": "Prompt cache control for providers that support it."
      +                    },
      +                    "file": {
      +                      "additionalProperties": false,
      +                      "properties": {
      +                        "file_data": {
      +                          "description": "Public file URL or base64 data URL.",
      +                          "minLength": 1,
      +                          "type": "string"
      +                        },
      +                        "filename": {
      +                          "type": "string"
      +                        }
      +                      },
      +                      "required": [
      +                        "file_data"
      +                      ],
      +                      "type": "object"
      +                    },
      +                    "type": {
      +                      "const": "file",
      +                      "type": "string"
      +                    }
      +                  },
      +                  "required": [
      +                    "type",
      +                    "file"
      +                  ],
      +                  "type": "object"
      +                }
      +              ]
      +            },
      +            "minItems": 1,
      +            "type": "array"
      +          }
      +        ]
      +      },
      +      "name": {
      +        "type": "string"
      +      },
      +      "role": {
      +        "const": "user",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "role",
      +      "content"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "content": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "items": {
      +              "$ref": "#/properties/messages/items/anyOf/0/properties/content/anyOf/1/items/anyOf/0"
      +            },
      +            "type": "array"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "name": {
      +        "type": "string"
      +      },
      +      "reasoning_content": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "reasoning_details": {
      +        "items": {
      +          "additionalProperties": false,
      +          "properties": {
      +            "data": {
      +              "type": "string"
      +            },
      +            "format": {
      +              "type": "string"
      +            },
      +            "id": {
      +              "type": "string"
      +            },
      +            "index": {
      +              "type": "number"
      +            },
      +            "text": {
      +              "type": "string"
      +            },
      +            "type": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "type"
      +          ],
      +          "type": "object"
      +        },
      +        "type": "array"
      +      },
      +      "role": {
      +        "const": "assistant",
      +        "type": "string"
      +      },
      +      "thought_signature": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "tool_calls": {
      +        "items": {
      +          "additionalProperties": false,
      +          "properties": {
      +            "function": {
      +              "additionalProperties": false,
      +              "properties": {
      +                "arguments": {
      +                  "type": "string"
      +                },
      +                "name": {
      +                  "type": "string"
      +                }
      +              },
      +              "required": [
      +                "name",
      +                "arguments"
      +              ],
      +              "type": "object"
      +            },
      +            "id": {
      +              "type": "string"
      +            },
      +            "thought_signature": {
      +              "type": "string"
      +            },
      +            "type": {
      +              "const": "function",
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "id",
      +            "type",
      +            "function"
      +          ],
      +          "type": "object"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "role"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "content": {
      +        "type": "string"
      +      },
      +      "name": {
      +        "type": "string"
      +      },
      +      "role": {
      +        "const": "tool",
      +        "type": "string"
      +      },
      +      "tool_call_id": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "role",
      +      "content",
      +      "tool_call_id"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "content": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "items": {
      +              "$ref": "#/properties/messages/items/anyOf/0/properties/content/anyOf/1/items/anyOf/0"
      +            },
      +            "minItems": 1,
      +            "type": "array"
      +          }
      +        ]
      +      },
      +      "name": {
      +        "type": "string"
      +      },
      +      "role": {
      +        "enum": [
      +          "system",
      +          "developer"
      +        ],
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "role",
      +      "content"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedInput schema / properties / messages / items / properties
      Removed value: -{
      -  "content": {
      -    "type": "string"
      -  },
      -  "role": {
      -    "enum": [
      -      "system",
      -      "user",
      -      "assistant"
      -    ],
      -    "type": "string"
      -  }
      -}
    • removedInput schema / properties / messages / items / required
      Removed value: -[
      -  "role",
      -  "content"
      -]
    • removedInput schema / properties / messages / items / type
      Removed value: -"object"
    • changedInput schema / properties / model / description
      Previous value: -"Model id. Defaults to venice-uncensored."New value: +"Model id. Defaults to deepseek-v4-flash-0731."
    • addedInput schema / properties / parallel_tool_calls
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / prompt_cache_key
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / prompt_cache_retention
      Added value: +{
      +  "enum": [
      +    "default",
      +    "extended",
      +    "24h"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / reasoning
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "effort": {
      +      "enum": [
      +        "none",
      +        "minimal",
      +        "low",
      +        "medium",
      +        "high",
      +        "xhigh",
      +        "max"
      +      ],
      +      "type": "string"
      +    },
      +    "summary": {
      +      "enum": [
      +        "auto",
      +        "concise",
      +        "detailed"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / reasoning_effort
      Added value: +{
      +  "$ref": "#/properties/reasoning/properties/effort",
      +  "description": "Takes precedence over reasoning.effort."
      +}
    • addedInput schema / properties / response_format
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": false,
      +      "properties": {
      +        "json_schema": {
      +          "additionalProperties": {},
      +          "type": "object"
      +        },
      +        "type": {
      +          "const": "json_schema",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "type",
      +        "json_schema"
      +      ],
      +      "type": "object"
      +    },
      +    {
      +      "additionalProperties": false,
      +      "properties": {
      +        "type": {
      +          "const": "json_object",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "type"
      +      ],
      +      "type": "object"
      +    },
      +    {
      +      "additionalProperties": false,
      +      "properties": {
      +        "type": {
      +          "const": "text",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "type"
      +      ],
      +      "type": "object"
      +    }
      +  ]
      +}
    • addedInput schema / properties / stop / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "type": "string"
      +    },
      +    "maxItems": 4,
      +    "minItems": 1,
      +    "type": "array"
      +  }
      +]
    • removedInput schema / properties / stop / items
      Removed value: -{
      -  "type": "string"
      -}
    • removedInput schema / properties / stop / maxItems
      Removed value: -8
    • removedInput schema / properties / stop / type
      Removed value: -"array"
    • addedInput schema / properties / timeout_ms
      Added value: +{
      +  "description": "Upstream timeout for this call, covering the full response body. Long generations may need more than the VENICE_HTTP_TIMEOUT_MS default.",
      +  "maximum": 600000,
      +  "minimum": 1000,
      +  "type": "integer"
      +}
    • addedInput schema / properties / tool_choice
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "none",
      +        "auto",
      +        "required"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "additionalProperties": false,
      +      "properties": {
      +        "function": {
      +          "additionalProperties": false,
      +          "properties": {
      +            "name": {
      +              "minLength": 1,
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "name"
      +          ],
      +          "type": "object"
      +        },
      +        "type": {
      +          "const": "function",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "type",
      +        "function"
      +      ],
      +      "type": "object"
      +    }
      +  ]
      +}
    • addedInput schema / properties / tools
      Added value: +{
      +  "items": {
      +    "anyOf": [
      +      {
      +        "additionalProperties": false,
      +        "properties": {
      +          "function": {
      +            "additionalProperties": false,
      +            "properties": {
      +              "description": {
      +                "type": "string"
      +              },
      +              "name": {
      +                "minLength": 1,
      +                "type": "string"
      +              },
      +              "parameters": {
      +                "$ref": "#/properties/response_format/anyOf/0/properties/json_schema"
      +              },
      +              "strict": {
      +                "type": "boolean"
      +              }
      +            },
      +            "required": [
      +              "name"
      +            ],
      +            "type": "object"
      +          },
      +          "id": {
      +            "type": "string"
      +          },
      +          "type": {
      +            "const": "function",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "function"
      +        ],
      +        "type": "object"
      +      },
      +      {
      +        "additionalProperties": false,
      +        "properties": {
      +          "type": {
      +            "enum": [
      +              "web_search",
      +              "x_search"
      +            ],
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "type"
      +        ],
      +        "type": "object"
      +      }
      +    ]
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / venice_parameters
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Venice-only options: web search, citations, system prompt control, reasoning control, and characters.",
      +  "properties": {
      +    "character_slug": {
      +      "description": "Public ID of a Venice character to answer in. Discoverable via venice_list_characters.",
      +      "type": "string"
      +    },
      +    "disable_thinking": {
      +      "description": "Turn reasoning off entirely on supported models, and strip the <think></think> blocks.",
      +      "type": "boolean"
      +    },
      +    "enable_web_citations": {
      +      "description": "Ask the model to cite web sources with ^1^ style superscripts. Only applies when web search ran.",
      +      "type": "boolean"
      +    },
      +    "enable_web_scraping": {
      +      "description": "Scrape URLs found in the latest user message and feed the contents to the model.",
      +      "type": "boolean"
      +    },
      +    "enable_web_search": {
      +      "description": "Web search. \"on\" forces it, \"auto\" leaves it to the model, \"off\" (default) disables it.",
      +      "enum": [
      +        "auto",
      +        "on",
      +        "off"
      +      ],
      +      "type": "string"
      +    },
      +    "enable_x_search": {
      +      "description": "Native xAI web + X/Twitter search, on supported models such as Grok. Runs server-side instead of Venice search.",
      +      "type": "boolean"
      +    },
      +    "include_venice_system_prompt": {
      +      "description": "Keep Venice's default system prompt alongside your own. Defaults to true; set false for full control of behaviour.",
      +      "type": "boolean"
      +    },
      +    "strip_thinking_response": {
      +      "description": "Remove <think></think> blocks from the response of a reasoning model.",
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / verbosity
      Added value: +{
      +  "description": "How much text the model returns.",
      +  "enum": [
      +    "low",
      +    "medium",
      +    "high",
      +    "auto"
      +  ],
      +  "type": "string"
      +}
  2. First observedv0.2.0

TDQS

A3.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes far beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false): non-streaming plaintext output, hard truncation at 8000 chars with omitted_chars reporting, completion id and resolved model in structured content, a TEE signature JSON block for X-Venice-TEE responses, explicit rejection of enable_e2ee, and both x402 wallet and API-key auth paths. This is exactly the behavioral context an agent needs before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tight, telegraphic sentences with zero filler; every clause carries a distinct fact (streaming mode, truncation, structured content, TEE, auth). Slightly list-like rather than organized by invocation order, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-parameter, nested-schema tool with no output schema, the description covers the operationally risky edges: truncation limits, what appears in structured content, and auth modes. Gaps remain around model selection policy and tool-calling/structured-output semantics, but the essentials an agent needs to avoid surprises are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 18 parameters and only 39% schema description coverage, the description is expected to compensate, but it only touches truncation length and the rejected enable_e2ee flag. It says nothing about temperature, top_p, tools/tool_choice, response_format, reasoning, prompt caching, or venice_parameters, leaving half the surface documented only by bare property names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'Run an OpenAI-compatible chat completion via Venice's text-model catalog' — which clearly separates it from image, video, TTS, and embedding siblings. It does not differentiate itself from the close siblings venice_responses or venice_chat_with_character, even though the schema points at venice_list_characters for characters.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage is clear (general text generation), and it adds two useful conditions: uncensored prompts allowed, and enable_e2ee is rejected. However, it never says when to prefer venice_responses or venice_chat_with_character over this plain chat endpoint, leaving the most likely sibling confusion unresolved.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.