TorkMCP Gateway • HITL • Tool Governance

The Universal Governance Layer for AI Agents

Enforce policies, block dangerous tools, and require human approval across |

Get Started Free View on GitHub
$ pip install tork-governance

# In 3 lines of code:
from tork import PolicyEngine
engine = PolicyEngine.from_yaml("policy.yaml")
result = engine.evaluate(agent_output)

Works with 12+ AI frameworks

LangChainCrewAIAutoGenOpenAIMCPAnthropicLlamaIndexFastAPIHugging FaceMistralSemantic KernelAWS Bedrock
LangChainCrewAIAutoGenOpenAIMCPAnthropicLlamaIndexFastAPIHugging FaceMistralSemantic KernelAWS Bedrock
LangChainCrewAIAutoGenOpenAIMCPAnthropicLlamaIndexFastAPIHugging FaceMistralSemantic KernelAWS Bedrock
12+
Frameworks Supported
<5ms
Evaluation Latency
100%
Local Processing
MIT
Open Source License
Features

Everything You Need for AI Governance

Enterprise-grade compliance without enterprise complexity

MCP Gateway

13 governance tools via Model Context Protocol. Drop-in integration with Claude, Cursor, and MCP clients.

Learn more →

Tool Call Governance

Block dangerous flags, enforce allowlists. Rate limiting and target environment restrictions.

Learn more →

HITL Systems

Human approval with fatigue detection. Velocity alerts catch slicing attacks.

Learn more →

Policy Enforcement

Define rules in YAML, enforce everywhere. Block, warn, or allow based on content.

Learn more →

PII Redaction

Automatically detect and redact 50+ PII types. Emails, phones, SSNs, credit cards.

Learn more →

Compliance Receipts

HMAC-signed, tamper-evident audit trails. Prove compliance with cryptographic certainty.

Learn more →

Listen Mode

Deploy in observation mode first. Tork learns your traffic patterns automatically.

Learn more →

Human-in-Loop

Route sensitive decisions to humans. Configurable escalation paths.

Learn more →

Framework Agnostic

Works with LangChain, CrewAI, AutoGen, or raw API calls.

Learn more →

Tork significantly reduces AI safety risks through multiple detection layers. No AI safety solution guarantees 100% protection. We recommend using Tork as part of a defense-in-depth strategy. See our Terms of Service for details.

How It Works

Three Steps to Governed AI

01

Define Policies

Write human-readable YAML policies.

policies:
  - name: pii-protection
    action: REDACT
    patterns: [email, phone]
02

Wrap Your Calls

Add Tork to your AI pipeline.

from tork import PolicyEngine
engine = PolicyEngine("policy.yaml")
result = engine.evaluate(output)
03

Monitor & Audit

Get dashboards and receipts.

# Every evaluation creates
# a signed receipt:
{
  "decision": "ALLOW",
  "hmac": "a3f2c1..."
}
Get Started

Install in Seconds

Python SDK for your codebase. MCP server for Claude & Cursor.

Python SDK
PyPI: tork-governance
$ pip install tork-governance
v0.7.0Python 3.10+
MCP Server
npm: @torknetwork/mcp-server
$ npx @torknetwork/mcp-server
v1.0.013 ToolsHITL

Works with Claude Desktop, Cursor, and any MCP-compatible client

View documentation on GitHub →
Zero Code Required

Configure Your Way

Three ways to manage AI governance. Pick what works for you.

No Code

Admin Console

Point and click. Embed our React dashboard directly in your app.

<TorkAdminConsole apiKey="..." />
Developers

SDK & API

Full programmatic control. Python, JavaScript, or REST API.

engine = GovernanceEngine(api_key="...")
AI Teams

AI-Assisted

Ask Claude or Cursor to configure governance for you.

"Register a tool that blocks --force flag"

All three methods write to the same database. Changes apply everywhere instantly.

Pricing

Start Free, Scale with Confidence

Open source core. Premium features for teams.

MonthlyAnnualSave 20%
OPEN SOURCE
Free
Forever, for everyone
  • Policy enforcement
  • PII redaction (10+ types)
  • Local audit logs
  • Community support
  • MIT licensed
Get Started
STARTER
$39/mo
Billed $468/year
  • Everything in Free
  • 50+ PII types
  • Cloud receipt storage
  • Email support
  • API access
POPULAR
PROFESSIONAL
$159/mo
Billed $1,908/year
  • Everything in Starter
  • Dashboard & analytics
  • SSO / SAML
  • Priority support
  • Custom policies
  • Webhooks
ENTERPRISE
Custom
For large organizations
  • Everything in Pro
  • Unlimited scale
  • On-prem deployment
  • Custom integrations
  • SLA guarantee
  • Dedicated support
Contact Sales

Ready to Govern Your AI?

Join developers building trustworthy AI systems with Tork.

Start Free Trial Star on GitHub