GitHubDashboard
Docs/Core Concepts

Core Concepts

Understand the fundamental building blocks of MCP Shield and how they work together to secure your AI tooling.

Architecture Overview

MCP Shield acts as a governed proxy between AI clients (like Cursor or Claude) and provider MCP servers (like GitHub or Vercel). This architecture enables centralized security controls without modifying your AI tools or provider integrations.

AI Clients
Cursor
Claude Desktop
VS Code
CI/CD Agents
MCP Shield Gateway
Policy Enforcement
DLP Scanning
Audit Logging
Credential Injection
Provider MCPs
GitHub
Vercel
Supabase
Figma

Core Principle

Provider credentials never reach the AI client. MCP Shield stores provider credentials securely and injects them only when forwarding requests. AI clients authenticate to MCP Shield with their own tokens, completely separate from provider access.

Key Components

MCP Gateway
The central proxy through which all MCP calls flow. It handles authentication, policy enforcement, DLP scanning, and audit logging.
  • Routes AI client requests to provider MCP servers
  • Injects provider credentials securely
  • Enforces security policies in real-time
  • Never exposes provider credentials to clients
Policy Engine
Real-time policy evaluation that determines whether an MCP call is allowed, modified, or denied based on your security rules.
  • Evaluate policies in under 100ms
  • Support complex conditions and rules
  • Allow, deny, or require approval
  • Provide clear explanations for decisions
DLP (Data Loss Prevention)
Scans MCP requests and responses for sensitive data patterns and prevents data exfiltration.
  • Detect PII, secrets, and sensitive patterns
  • Block or redact sensitive data
  • Customizable detection rules
  • Real-time scanning with minimal latency
Provider Connections
Secure, OAuth-based connections to external providers like GitHub, Vercel, and Supabase.
  • One-click OAuth authentication
  • Scoped permissions per provider
  • Automatic token refresh
  • Credential encryption at rest
MCP Shield Tokens
Authentication tokens that clients use to access the MCP Shield gateway. Separate from provider credentials.
  • User tokens for interactive use
  • Service tokens for automation
  • Scoped permissions and access controls
  • Expiration and rotation support
Audit Logging
Complete, tamper-evident audit trail of every MCP invocation for compliance and security investigations.
  • Every call is logged
  • Configurable retention policies
  • Export to SIEM systems
  • Full request/response capture (optional)

Request Flow

When an AI client makes an MCP call through MCP Shield, the following happens:

1

Client Authentication

The client presents an MCP Shield token. The gateway validates the token and extracts the user/tenant context.

2

Policy Evaluation

The request is evaluated against your security policies. The policy engine determines if the call should proceed.

3

DLP Scanning

The request payload is scanned for sensitive data patterns. Detected patterns can trigger blocks or redactions.

4

Credential Injection

MCP Shield retrieves the provider credentials from secure storage and injects them into the forwarded request.

5

Provider Request

The request is forwarded to the provider MCP server with proper authentication. The response is captured.

6

Response Processing

The response is scanned for sensitive data, logged to the audit trail, and returned to the client.

Continue Learning