Skip to main content
When skills are exposed over HTTP (via skillsConfig.enabled), FrontMCP supports four authentication modes to protect skill endpoints.

Auth Modes

Configuration

Public Mode

Disable authentication on skill endpoints regardless of the parent server’s auth.

API Key Mode

Clients authenticate with either header format:
API key comparison uses timing-safe equality to prevent timing attacks. All configured keys are checked even after a match is found to maintain constant-time behavior.

JWT Bearer Mode

JWT tokens are validated against the issuer’s JWKS endpoint (auto-discovered from {issuer}/.well-known/jwks.json).

Validation Result

The validator returns a structured result:

Factory Function

Use createSkillHttpAuthValidator() to create a validator from skill config:

Tool Authorization Guard

When a skill session is active, the Tool Authorization Guard enforces which tools the skill is allowed to call. This prevents skill sessions from accessing tools outside their declared allowlist.

Policy Modes

Usage

Error Types

ToolNotAllowedError

Thrown when a tool is not in the skill’s allowlist (strict mode).

ToolApprovalRequiredError

Thrown when a tool requires approval but has not been approved yet.