Feature

MCP Security

Purpose-built security layer for Model Context Protocol. Validate every tool call, prevent prompt injection, block unauthorized access, and enforce granular policies across Claude, Cursor, and Windsurf agents.

MCP Threat Landscape

MCP gives AI agents the ability to read files, query databases, make API calls, and execute code. Without a security layer, a single misconfigured tool can expose customer data, delete infrastructure, or exfiltrate secrets.

Prompt Injection

Malicious instructions embedded in tool outputs that hijack agent behaviour. Tork scans tool responses for injection patterns before they reach the model.

Unauthorized Access

Agents calling tools they shouldn't have access to. Tork enforces tool allowlists and denylists per agent, per policy, per environment.

Data Exfiltration

Sensitive data leaking through tool call parameters or responses. Tork scans all MCP traffic for PII and blocks or redacts before transmission.

SSRF & Network Attacks

Tool calls that reach internal services or make requests to attacker-controlled URLs. Tork validates URLs and blocks internal network access.

How It Works

1

Intercept

Every MCP tool call is intercepted before execution. The tool name, parameters, and context are captured for evaluation.

2

Validate

Parameters are validated against your policy rules. Input is scanned for PII, injection patterns, and malicious payloads. URLs are checked against allowlists.

3

Enforce

Based on policy evaluation: allow the call, block it, redact sensitive parameters, or escalate to a human reviewer for approval.

4

Audit

Every decision generates an HMAC-signed compliance receipt with full context. Receipts are hash-chained for tamper detection.

Security Features

Tool Allowlisting

Explicitly define which tools each agent can access. Everything else is blocked by default.

Parameter Validation

Type-check, range-check, and pattern-match every parameter against your schema.

PII Scanning

50+ PII types detected in tool call inputs and outputs. Redact before the model sees it.

Rate Limiting

Per-tool, per-agent rate limits prevent abuse and runaway agents.

URL Allowlisting

Block SSRF by restricting which URLs and domains tools can access.

Injection Detection

Pattern matching for common prompt injection techniques in tool responses.

Kill Switch

Emergency stop any agent instantly via API call or MCP tool.

Tamper-Proof Audit

HMAC hash-chained receipts for every tool call. Exportable for compliance.

Real-Time Alerts

Webhook notifications for blocked calls, PII detections, and policy violations.

Policy Configuration

Define security policies in YAML. Tork evaluates every MCP tool call against your rules in under 1ms.

policy.yaml

# MCP Security Policy
version: "1.0"

tools:
  # Allow specific tools
  allowed:
    - read_file
    - search_code
    - run_tests

  # Block dangerous tools
  blocked:
    - delete_file
    - execute_shell
    - send_email

  # Require human approval
  escalate:
    - deploy_production
    - modify_database

security:
  # PII scanning on all tool calls
  scan_pii: true
  pii_action: redact  # allow | redact | block

  # URL restrictions
  url_allowlist:
    - "*.company.com"
    - "api.github.com"

  # Rate limits
  rate_limit:
    per_tool: 100/minute
    per_agent: 500/minute

  # Injection detection
  scan_injections: true
  injection_action: block

Quick Integration

Python

from tork import TorkGovernance

tork = TorkGovernance(
    api_key="tork_...",
    policy="policy.yaml"
)

# Wrap any MCP tool call
result = tork.govern_tool_call(
    tool="read_file",
    params={"path": "/etc/passwd"},
)

if result.action == "block":
    print(f"Blocked: {result.reason}")
else:
    # Safe to execute
    execute_tool(result.sanitized_params)

JavaScript / TypeScript

import { TorkGovernance } from 'tork-governance';

const tork = new TorkGovernance({
  apiKey: 'tork_...',
  policy: 'policy.yaml',
});

// Wrap any MCP tool call
const result = await tork.governToolCall({
  tool: 'read_file',
  params: { path: '/etc/passwd' },
});

if (result.action === 'block') {
  console.log(`Blocked: ${result.reason}`);
} else {
  // Safe to execute
  await executeTool(result.sanitizedParams);
}

Works With Every MCP Client

Claude Desktop
Cursor
Windsurf
Claude Code
Continue
Any MCP Client

Tork's MCP security layer works as a transparent proxy. No changes to your MCP server code required — just point your client config at the Tork gateway.

Compliance Ready

SOC 2
GDPR
HIPAA
PCI DSS
ISO 27001
NIST AI RMF

Every tool call generates a blockchain-verified audit receipt. Export your complete governance history for compliance reporting and security audits.

Secure Your MCP Agents Today

Add security to every tool call in minutes. Free tier available.

Start Free Trial See MCP Gateway