MCP Tools for AI Governance
Add AI safety guardrails directly to Claude Desktop, Cursor, and other MCP-compatible clients. 25 governance tools including PII detection, tool governance, HITL, and cloud API integration.
What is MCP?
Model Context Protocol enables AI assistants to use external tools
The Model Context Protocol (MCP) is an open standard that allows AI assistants like Claude to interact with external tools and services. The Tork MCP Server provides governance tools for PII scanning, tool call validation, human-in-the-loop approvals, and more.
PII Detection
Scan and redact sensitive data
Tool Governance
Control which tools agents can call
Human-in-the-Loop
Approval workflows with fatigue detection
Cloud Integration
Sync with Tork Cloud API
Installation
Install the Tork MCP server globally or use npx
Option 1: Install globally
Option 2: Use npx (recommended)
Using npx in your configuration ensures you always have the latest version.
Configuration
Set up Tork MCP in your favorite AI client
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Cursor
Add to your Cursor settings (.cursor/mcp.json in your project):
Set TORK_API_KEY to enable Cloud API tools. Without it, only local tools (PII scanning, tool governance, HITL) are available.
Using Tork Tools
Tools are called automatically by the AI based on your requests
Once configured, simply ask Claude (or your AI assistant) to perform governance tasks. The AI will automatically select and call the appropriate Tork tools.
Practical Workflow
Complete governance workflow with tool registration and HITL
Available Tools (25)
Click to expand tool details and parameters
Ready to Get Started?
Get your API key and start using Tork governance tools in your AI workflow today.