thinkneo_evaluate_guardrail
ActiveTool of ThinkNEO MCP Server
declared in 1.28.0
Evaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider. Returns risk assessment, violations found, and recommendations. Requires authentication.
Parameters schema
{
"type": "object",
"title": "thinkneo_evaluate_guardrailArguments",
"required": [
"text",
"workspace"
],
"properties": {
"text": {
"type": "string",
"title": "Text",
"description": "The prompt or text content to evaluate for policy violations (max 32,000 characters)"
},
"workspace": {
"type": "string",
"title": "Workspace",
"description": "Workspace whose guardrail policies to apply for this evaluation"
},
"guardrail_mode": {
"type": "string",
"title": "Guardrail Mode",
"default": "monitor",
"description": "Evaluation mode: 'monitor' (log violations only) or 'enforce' (block the request on violation)"
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
ThinkNEO MCP Server
https://github.com/thinkneo-ai/mcp-server
3/7 registries