Dingdawg Code Review

A local npm MCP server for AI code review covering security, quality and performance, with signed governance receipts for each action.

What you can do

Run AI code review focused on security, quality and performance issues, per the registry description and the code-review package listed among the governed-agent packages. Learn and apply the user's own patterns over time. Produce cryptographically signed receipts recording what an agent decided, why, which model and version, and when. Route agent calls through metered, audited governed execution and retrieve compliance classification, regulation lookup, and agent trust scores. The manifest lists no individual tools, so exact tool names and inputs are not documented here.

When to use it

Worth considering when you want an assistant to review code for security, quality and performance problems and to keep an auditable, signed record of what the agent did, for example when working toward AI Act or NIST AI RMF style evidence.

Requirements

Runs as a local process over stdio, installed from the npm package dingdawg-code-review, so Node.js and npm are needed. A DINGDAWG_API_KEY environment variable is required for paid tier access; the README says a key is issued at developer signup and shown once. Network access to the provider's API is implied by the architecture.