Analyze code for security vulnerabilities, quality issues, and performance bottlenecks with AI-powered reviews that learn your codebase patterns. Built for developers who want automated, receipted code audits without manual review overhead.
io.github.dingdawg/dingdawg-code-review
Local install
STDIO
No auth required
How models use it and what it is built for.
Analyze code for security vulnerabilities, quality issues, and performance bottlenecks with AI-powered reviews that learn your codebase patterns. Built for developers who want automated, receipted code audits without manual review overhead.
Local install — runs as a subprocess.
Configuration this server reads at startup.
API key for paid tier access — get free at dingdawg.com
Where to find authoritative docs and source for Dingdawg Code Review.
Paste any of these into Agent Studio after connecting Dingdawg Code Review.
Common questions about connecting and running Dingdawg Code Review.
What types of code issues does dingdawg-code-review detect?
The server identifies security vulnerabilities, code quality problems, and performance bottlenecks. It learns from your codebase patterns over time to provide increasingly tailored feedback.
How do I set up dingdawg-code-review and get started?
Install via `npx dingdawg-code-review@2.0.6`, then set the DINGDAWG_API_KEY environment variable. Free tier access is available at dingdawg.com; upgrade to paid tier for full capabilities.
Is there a free tier, and what does paid access unlock?
Yes, free tier access is available at dingdawg.com. The DINGDAWG_API_KEY environment variable grants access to paid tier features with enhanced review depth and pattern learning.
What does 'receipted' mean in the context of code reviews?
Receipted reviews provide documented, traceable audit records of code analysis. This is useful for compliance and accountability in teams that need to track security and quality decisions.
Can dingdawg-code-review learn from my team's coding standards?
Yes, the server learns your codebase patterns over time to provide increasingly personalized reviews. This means feedback becomes more aligned with your team's specific practices and priorities.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams