thinkneo_complete

Active

declared in 1.28.0

Run a governed LLM completion through the ThinkNEO AI gateway. The request is authorized, classified, and policy-checked against your workspace governance BEFORE any provider is called — a blocked prompt never reaches the model. Tenant/workspace are derived from your API key.

Parameters schema

{
  "type": "object",
  "title": "thinkneo_completeArguments",
  "required": [
    "prompt"
  ],
  "properties": {
    "model": {
      "type": "string",
      "title": "Model",
      "default": "anthropic/claude-haiku-4-5-20251001",
      "description": "provider/model, e.g. 'anthropic/claude-haiku-4-5-20251001'"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "description": "The user prompt to complete"
    },
    "system": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "System",
      "default": null,
      "description": "Optional system instruction"
    },
    "max_tokens": {
      "type": "integer",
      "title": "Max Tokens",
      "default": 256,
      "description": "Max output tokens"
    },
    "temperature": {
      "type": "number",
      "title": "Temperature",
      "default": 0.7,
      "description": "Sampling temperature"
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

ThinkNEO MCP Server

https://github.com/thinkneo-ai/mcp-server

3/7 registries

View full server →