This server provides a production-readiness audit engine for AI-built apps, enabling deterministic project scanning, scoring, and remediation planning via an MCP interface.

• describe: Retrieve the full CheckYourself capability manifest, including commands, schemas, scoring rules, and MCP capabilities.

• scan: Run deterministic local discovery and obvious-risk checks (e.g., committed secrets, debug flags, wildcard CORS, missing lockfiles) against a project path, with an optional deep validation mode.

• coverage_emit: Generate a 20-surface coverage skeleton for an AI agent to populate with evidence during a full diagnostic audit.

• coverage_check: Validate a filled coverage object for completeness and evidence requirements, flagging incomplete or missing entries.

• score: Compute the deterministic Production Reality Score (0–100) from findings and optional coverage data, applying severity caps so serious risks cannot be hidden behind polish.

• backlog: Prioritize all findings into a complete remediation backlog ordered by harm, reversibility, and learning value, and propose a first approval-ready fix batch.

• next: Return the next safest unresolved approval batch from current findings, enabling a guided, incremental fix loop.

• validate: Check a JSON artifact against a bundled CheckYourself schema subset to ensure structural correctness.

• schema: Fetch a specific bundled JSON schema by name for use in validation or agent workflows.

Integrates with GitHub Copilot to provide pre-launch production-readiness audits for AI-built applications, leveraging file-reading capabilities for diagnostics.

Allows Replit users to run CheckYourself audits directly in the Replit environment, using its file-aware agents to perform read-only production checks.