Review UI code directly in the browser and let AI agents automatically fix issues via MCP. Built for developers who want human-in-the-loop code review with automated remediation.
io.github.0ics-srls/ui-ticket-mcp
Local install
STDIO
1 required env var
How models use it and what it is built for.
Review UI code directly in the browser and let AI agents automatically fix issues via MCP. Built for developers who want human-in-the-loop code review with automated remediation.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Root directory of the project being reviewed
HTTP port for REST API (default: 3200)
Where to find authoritative docs and source for ui-ticket.
Paste any of these into Agent Studio after connecting ui-ticket.
Common questions about connecting and running ui-ticket.
What is ui-ticket-mcp and how does it work?
It's an MCP server that bridges human code review in the browser with AI-powered code fixes. You review UI code in a browser interface, and AI agents connected via MCP can automatically apply fixes to your codebase.
What environment variables do I need to set up?
PROJECT_ROOT is required and should point to your project's root directory. REVIEW_PORT is optional (defaults to 3200) and controls which HTTP port the REST API runs on.
Can I use this with a monorepo?
Yes, set PROJECT_ROOT to your monorepo root. The server will serve the REST API on the configured REVIEW_PORT so you can review and fix code across multiple packages.
How do I start the server?
Run `uvx ui-ticket-mcp@1.4.0` with PROJECT_ROOT set as an environment variable. The server communicates via stdio and exposes a REST API on REVIEW_PORT for the browser review interface.
What happens after I review code in the browser?
Review tickets are created and passed to AI agents via MCP. The agents can then read the tickets and apply fixes directly to your project files based on the review feedback.
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