Exposes audit tools over the Model Context Protocol so MCP clients such as Claude Desktop can run scoped, sandboxed defensive web-security audits without an API key.
Enables users to expose temporal architectural memory, privacy sanitization, and local test-runner capabilities as MCP tools so clients like Claude Desktop, Cursor, and Hermes Agent can query decisions, sanitize prompts, and verify code changes.
Enables continuing a local coding task from your own web ChatGPT account by exposing project-scoped read and apply tools over MCP, with no inference API dependency.
Enables exposing product capabilities to ChatGPT, Claude, and other MCP clients via a stateless Streamable HTTP endpoint with OAuth resource binding and structured-output helpers.
Enables ChatGPT and other MCP clients to securely read Health Connect-derived health and training history, retrieve daily readiness and workout briefs, save schema-validated coach reports, and trigger email delivery through OAuth-protected tools.