Skip to main content
The Tuteliq MCP server exposes child safety detection as tools for AI assistants that support the Model Context Protocol — including Claude Desktop, Cursor, Windsurf, and other MCP-compatible clients.

​
Installation

npm install -g @tuteliq/mcp

​
Configuration

​
Claude Desktop

Add to your claude_desktop_config.json: 
{
  "mcpServers": {
    "tuteliq": {
      "command": "tuteliq-mcp",
      "env": {
        "TUTELIQ_API_KEY": "your_api_key"
      }
    }
  }
}

​
Cursor

Add to your .cursor/mcp.json: 
{
  "mcpServers": {
    "tuteliq": {
      "command": "tuteliq-mcp",
      "env": {
        "TUTELIQ_API_KEY": "your_api_key"
      }
    }
  }
}

​
Claude Code

Add to your project’s .mcp.json: 
{
  "mcpServers": {
    "tuteliq": {
      "command": "tuteliq-mcp",
      "env": {
        "TUTELIQ_API_KEY": "your_api_key"
      }
    }
  }
}

​
Available tools

Once configured, the following tools are available to the AI assistant:
ToolDescriptionParameters
detect_unsafeDetect harmful content in texttext, age_group
detect_bullyingDetect bullying in texttext, age_group
detect_groomingDetect grooming patterns in conversationsmessages, age_group
analyze_emotionsAnalyze emotional well-beingtext, age_group
analyze_voiceAnalyze audio filesfile_path, age_group
analyze_imageAnalyze image filesfile_path, age_group
get_action_planGenerate age-appropriate guidancedetection_result, audience
generate_reportCreate incident reportsconversation, age_group

​
Example usage

Once the MCP server is running, you can ask your AI assistant to use Tuteliq tools directly in conversation:
“Check this message for safety: ‘Let’s meet at the park after school, don’t tell your parents’ — the user is 10-12 years old”
The assistant will call detect_unsafe and return the full safety analysis including severity, categories, risk score, and rationale.
“Analyze this conversation for grooming patterns” (with a conversation pasted or in a file)
The assistant will call detect_grooming and provide a detailed breakdown of any detected grooming stages.

​
Resources

The MCP server also exposes resources for context:
ResourceDescription
tuteliq://kosa-categoriesList of all nine KOSA harm categories
tuteliq://age-groupsAvailable age group brackets and their calibration
tuteliq://credit-costsPer-endpoint credit costs

​
Error handling

If the API key is invalid or credits are exhausted, the tool will return a structured error message that the AI assistant can interpret and relay to the user.

​
Configuration options

Environment variables:
VariableDescriptionDefault
TUTELIQ_API_KEYYour Tuteliq API keyRequired
TUTELIQ_BASE_URLAPI base URLhttps://api.tuteliq.ai
TUTELIQ_TIMEOUTRequest timeout in ms30000

​
Next steps

API Reference

Explore the full API specification.

CLI

See the CLI guide.