Skip to main content
Glama
veniceai

Venice MCP Server

Official
by veniceai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Venice Responses API

venice_responses

Generate text responses from Venice models with text/image input, reasoning controls, web search, scraping, and character prompts using API key or x402 wallet auth.

Instructions

Alpha, stateless OpenAI-compatible Responses API for Venice text models. Supports text/image input and reasoning controls, but this MCP tool does not advertise tool calling because the endpoint does not reliably accept those fields. E2EE-capable models are not supported. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key.

Input Schema

NameRequiredDescriptionDefault
inputYesPlain text or an array of text/image message inputs.
modelNo
top_pNo
reasoningNo
temperatureNo
max_output_tokensNo
venice_parametersNoVenice-only options supported by /responses: web search, citations, scraping, system prompt control, characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.3.0
    • changedInput schema / properties / input / anyOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "items": {
-      "additionalProperties": false,
-      "properties": {
-        "content": {
-          "type": "string"
-        },
-        "role": {
-          "enum": [
-            "system",
-            "user",
-            "assistant"
-          ],
-          "type": "string"
-        }
-      },
-      "required": [
-        "role",
-        "content"
-      ],
-      "type": "object"
-    },
-    "type": "array"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "additionalProperties": false,
+      "properties": {
+        "content": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "items": {
+                "anyOf": [
+                  {
+                    "additionalProperties": false,
+                    "properties": {
+                      "text": {
+                        "type": "string"
+                      },
+                      "type": {
+                        "enum": [
+                          "input_text",
+                          "text",
+                          "output_text"
+                        ],
+                        "type": "string"
+                      }
+                    },
+                    "required": [
+                      "type",
+                      "text"
+                    ],
+                    "type": "object"
+                  },
+                  {
+                    "additionalProperties": false,
+                    "properties": {
+                      "image_url": {
+                        "anyOf": [
+                          {
+                            "minLength": 1,
+                            "type": "string"
+                          },
+                          {
+                            "additionalProperties": false,
+                            "properties": {
+                              "detail": {
+                                "enum": [
+                                  "auto",
+                                  "low",
+                                  "high"
+                                ],
+                                "type": "string"
+                              },
+                              "url": {
+                                "minLength": 1,
+                                "type": "string"
+                              }
+                            },
+                            "required": [
+                              "url"
+                            ],
+                            "type": "object"
+                          }
+                        ]
+                      },
+                      "type": {
+                        "enum": [
+                          "input_image",
+                          "image_url"
+                        ],
+                        "type": "string"
+                      }
+                    },
+                    "required": [
+                      "type",
+                      "image_url"
+                    ],
+                    "type": "object"
+                  }
+                ]
+              },
+              "minItems": 1,
+              "type": "array"
+            }
+          ]
+        },
+        "role": {
+          "enum": [
+            "system",
+            "developer",
+            "user",
+            "assistant"
+          ],
+          "type": "string"
+        },
+        "type": {
+          "const": "message",
+          "type": "string"
+        }
+      },
+      "required": [
+        "role",
+        "content"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  }
+]
    • changedInput schema / properties / input / description
      Previous value: -"Either a plain string or an array of role+content messages."New value: +"Plain text or an array of text/image message inputs."
    • 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 / top_p
      Added value: +{
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}
    • addedInput schema / properties / venice_parameters
      Added value: +{
+  "additionalProperties": false,
+  "description": "Venice-only options supported by /responses: web search, citations, scraping, system prompt control, characters.",
+  "properties": {
+    "character_slug": {
+      "description": "Public ID of a Venice character to answer in. Discoverable via venice_list_characters.",
+      "type": "string"
+    },
+    "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"
+    },
+    "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"
+    }
+  },
+  "type": "object"
+}
  2. First observedv0.2.0

TDQS

A3.9/5.0
Behavior5/5

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

Given annotations only cover a generic safety profile, the description carries the real burden and does so well: alpha/stateless status, deliberate omission of tool calling because the endpoint is unreliable, E2EE models unsupported, NSFW allowed where the model permits, and both x402 wallet and API-key auth paths.

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?

Four tight sentences, front-loaded with what the tool is, then limitations, then capabilities and auth. Dense but each clause carries distinct information; only the auth sentence feels slightly appended.

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 a 7-parameter nested-schema tool with no output schema, the description covers identity, limitations, input modalities, and auth adequately. It does not describe the response shape, though 'OpenAI-compatible Responses API' gives a strong prior.

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

Parameters3/5

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

Schema description coverage is only 29%, but the description adds only broad hints (text/image input, reasoning controls) rather than explaining model selection, temperature, or the venice_parameters contents. The nested venice_parameters subfields do carry their own schema descriptions, so the heavy lifting is partly done there.

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?

Starts with a specific verb/resource framing: a stateless, OpenAI-compatible Responses API for Venice text models, supporting text/image input and reasoning controls. That distinguishes it clearly from siblings like venice_chat and venice_embeddings, though it never states the distinction explicitly.

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?

Usage context is implied (stateless Responses-style generation with reasoning controls, no tool calling) but there is no explicit 'use this when / use venice_chat instead when' guidance, which matters given the large sibling set of generation tools.

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

Deploy Server

Other Tools