Security & Privacy

The Race Engineer is designed with security at every layer. Your racing data is protected by sandbox isolation, per-query ownership verification, and industry-standard authentication.

Sandbox Isolation

AI code runs in isolated-vm, a V8 isolate with no access to:

• Network: Cannot make HTTP requests or connect to external services
• Filesystem: Cannot read or write files
• Environment: Cannot access environment variables or secrets
• Modules: Cannot require() or import external packages

The sandbox is constrained to:

Limit	Value
Execution timeout	10 seconds
Memory	32 MB
API calls per execution	20
Code size	10 KB
Output size	100 KB

If any limit is exceeded, execution is terminated immediately.

Data Ownership

Every function verifies that the authenticated user owns the requested data:

• assertSessionOwnership(userId, sessionId) before any session query
• assertRaceOwnership(userId, raceEventId) before calendar operations
• assertNotepadOwnership(userId, notepadId) before notepad access

There is no way to query another user’s data — even if you know their session IDs. The one exception is a public leaderboard lap you explicitly duel with compareTraces, which is only readable because its owner opted to share it publicly.

Input Validation

All functions use Zod schemas with strict validation:

• MUTATING and CREATIVE functions use .strict() — unknown fields cause errors
• Every parameter has a .describe() annotation explaining its purpose
• Type coercion is disabled — the AI must pass the correct types
• The _validateOnly: true flag lets AI dry-run mutations without writing

This prevents prompt injection attacks where an AI might try to pass unexpected parameters.

Authentication

The server uses OAuth 2.0 with PKCE (Proof Key for Code Exchange):

1. Dynamic client registration — AI clients register automatically
2. Authorization code flow — User explicitly grants access via consent page
3. PKCE mandatory — Prevents authorization code interception
4. JWT tokens — Access tokens are signed and verified on every request
5. Refresh tokens — Automatic token renewal without re-authorization

Discovery Endpoints

The server follows RFC 8414 and RFC 9728 for automatic discovery:

Endpoint	Standard	Purpose
/.well-known/oauth-authorization-server	RFC 8414	OAuth metadata discovery
/.well-known/oauth-protected-resource	RFC 9728	Resource metadata with 401 WWW-Authenticate

Clients supporting MCP over Streamable HTTP and OAuth can use these endpoints for discovery. Configuration steps vary by client.

CORS Policy

The server allows requests from known AI platforms:

• https://claude.ai
• https://chatgpt.com
• https://chat.openai.com
• Plus custom origins configured by the server operator

Data Handling

• Model training: The Race Engineer does not train its own model on your telemetry. A connected AI client’s provider may process requested results under its own terms.
• Account access: Queries are scoped to your authenticated account; requested results pass to the AI client you authorize.
• Soft deletes: Most data uses deleted_at timestamps — accidental deletions can be recovered
• Null stripping: Output is cleaned of null values to reduce token usage

What We Don’t Store

The Race Engineer does not store:

• AI conversation history
• The code that AI writes (executed and discarded)
• AI model responses
• Your AI client’s API keys or credentials