Security

The AI Gateway provides powerful security features to protect your data and prevent abuse. Block sensitive information from being sent to AI providers, and stop malicious users from exploiting your applications.

Sensitive Data Protection

The Risk

When using AI assistants or building AI-powered apps, sensitive data can accidentally be exposed:

Real scenarios we’ve seen:

AWS keys sent in code context to ChatGPT
Database passwords included in error messages
Customer PII processed by AI for “analysis”
API secrets in environment variable debugging

Automatic Detection

The gateway scans all requests for sensitive patterns:

Detected patterns include:

AWS Access Keys and Secret Keys
GitHub Personal Access Tokens
Database connection strings
API keys (various providers)
Private keys (RSA, SSH, etc.)
Credit card numbers
Social Security Numbers
Email addresses
Phone numbers

Blocking Sensitive Data

Configure the gateway to block requests containing sensitive data:

// Configure blocking rules
await leanmcp.gateway.setSecurityRules({
  blockPatterns: [
    { type: 'aws_key', action: 'block' },
    { type: 'api_key', action: 'block' },
    { type: 'password', action: 'warn' },
  ],
  alertOnDetection: true,
});

Action Types

Action	Behavior
block	Request is rejected, never sent to AI provider
warn	Request proceeds but alert is generated
redact	Sensitive data is replaced with [REDACTED] before sending
log	Request proceeds, logged for review

Remediation

When sensitive data is detected:

Review the log - see exactly what was exposed
Rotate credentials - change any exposed secrets immediately
Update your code - ensure secrets aren’t in files that get sent to AI
Enable blocking - prevent future exposure

Keep secrets in .env files and ensure .env is in your .gitignore. Most AI assistants respect gitignore patterns.

Blocking Malicious Users

When building AI-powered applications, you need to protect against abuse.

Common Abuse Patterns

Prompt Injection

Users trying to manipulate your AI to bypass restrictions

Cost Attacks

Users making excessive requests to run up your AI costs

Data Extraction

Attempts to extract training data or system prompts

Jailbreaking

Trying to make the AI produce harmful content

User Blocking

Block abusive users instantly:

// Block a user via API
await leanmcp.gateway.blockUser({
  userId: 'abusive-user-123',
  reason: 'Excessive usage and prompt injection attempts',
  duration: 'permanent', // or '24h', '7d', etc.
});

When a blocked user makes a request:

Request is immediately rejected
No tokens are consumed
Event is logged for audit

Unblocking Users

// Unblock a user
await leanmcp.gateway.unblockUser({
  userId: 'user-123',
  reason: 'Issue resolved, user warned',
});

Viewing Blocked Users

Access the block list in your dashboard:

Navigate to AI Gateway > Security > Blocked Users
View all blocked users with reasons and timestamps
Manage blocks (extend, reduce, remove)

Rate Limiting

Prevent abuse with intelligent rate limiting:

// Set rate limits
await leanmcp.gateway.setRateLimit({
  scope: 'per_user',
  limits: {
    requestsPerMinute: 20,
    requestsPerHour: 200,
    tokensPerDay: 500000,
    maxCostPerMonth: 100.00,
  },
  action: 'block', // or 'queue', 'throttle'
});

Rate Limit Strategies

Strategy	Use Case
Per User	Limit individual user consumption
Per IP	Prevent anonymous abuse
Per API Key	Limit by integration
Global	Overall service protection

Handling Rate Limits

When users hit limits:

// Client receives 429 response
{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Too many requests. Please try again in 60 seconds.",
    "retry_after": 60
  }
}

Content Filtering

Block requests based on content:

Input Filtering

// Block certain input patterns
await leanmcp.gateway.setContentFilter({
  inputFilters: [
    { pattern: 'ignore previous instructions', action: 'block' },
    { pattern: 'reveal your system prompt', action: 'block' },
    { pattern: /jailbreak/i, action: 'warn' },
  ]
});

Output Filtering

// Filter AI responses
await leanmcp.gateway.setContentFilter({
  outputFilters: [
    { pattern: 'internal_api_endpoint', action: 'redact' },
    { pattern: /\b\d{4}-\d{4}-\d{4}-\d{4}\b/, action: 'redact' }, // Credit cards
  ]
});

Audit Logging

All security events are logged:

Event Type	Details Logged
blocked_request	User, reason, request content
sensitive_data_detected	Pattern, location, severity
rate_limit_hit	User, limit type, current count
user_blocked	User, reason, admin who blocked
user_unblocked	User, reason, admin who unblocked

Export Audit Logs

For compliance and review:

curl -X GET "https://api.leanmcp.com/gateway/audit-logs?days=30" \
  -H "Authorization: Bearer your-api-key" \
  -o audit-logs.json

Security Alerts

Get notified of security events:

Alert Configuration

await leanmcp.gateway.createSecurityAlert({
  events: ['sensitive_data_detected', 'rate_limit_exceeded', 'suspicious_pattern'],
  channels: {
    email: ['[email protected]'],
    slack: 'https://hooks.slack.com/...',
    webhook: 'https://your-server.com/alerts',
  },
  severity: 'medium', // or 'low', 'high', 'critical'
});

Alert Examples

Best Practices

Start with warn, then block

Begin with ‘warn’ actions to understand what would be blocked, then switch to ‘block’ once tuned.

Review blocks regularly

Check blocked requests weekly to ensure legitimate users aren’t being affected.

Set up alerts early

Configure security alerts before launch so you’re notified of issues immediately.

Use appropriate rate limits

Set limits that allow normal use while preventing abuse. Adjust based on observed patterns.

Document your policies

Make sure users know your usage policies and what behavior will result in blocking.

Overview

For Users

For Developers

Features

Security

Security

Sensitive Data Protection

The Risk

Automatic Detection

Blocking Sensitive Data

Action Types

Remediation

Blocking Malicious Users

Common Abuse Patterns

Prompt Injection

Cost Attacks

Data Extraction

Jailbreaking

User Blocking

Unblocking Users

Viewing Blocked Users

Rate Limiting

Rate Limit Strategies

Handling Rate Limits

Content Filtering

Input Filtering

Output Filtering

Audit Logging

Export Audit Logs

Security Alerts

Alert Configuration

Alert Examples

Best Practices

Next Steps

Observability

Token Optimization

Overview

For Users

For Developers

Features

​Security

​Sensitive Data Protection

​The Risk

​Automatic Detection

​Blocking Sensitive Data

​Action Types

​Remediation

​Blocking Malicious Users

​Common Abuse Patterns

Prompt Injection

Cost Attacks

Data Extraction

Jailbreaking

​User Blocking

​Unblocking Users

​Viewing Blocked Users

​Rate Limiting

​Rate Limit Strategies

​Handling Rate Limits

​Content Filtering

​Input Filtering

​Output Filtering

​Audit Logging

​Export Audit Logs

​Security Alerts

​Alert Configuration

​Alert Examples

​Best Practices

​Next Steps

Observability

Token Optimization

Security

Sensitive Data Protection

The Risk

Automatic Detection

Blocking Sensitive Data

Action Types

Remediation

Blocking Malicious Users

Common Abuse Patterns

User Blocking

Unblocking Users

Viewing Blocked Users

Rate Limiting

Rate Limit Strategies

Handling Rate Limits

Content Filtering

Input Filtering

Output Filtering

Audit Logging

Export Audit Logs

Security Alerts

Alert Configuration

Alert Examples

Best Practices

Next Steps