ui-ticket-mcp
This bridges visual UI review and AI-assisted fixes by letting you click elements in the browser, leave comments like "this button should be blue," then having your AI agent read those annotations via MCP and fix the underlying code. The Python server exposes 10 tools over stdio including get_annotated_reviews (returns CSS selectors, DOM paths, computed styles, accessibility metadata), resolve_review, and get_pending_work. A web component drops into any framework to render the review panel and annotation UI. Reviews live in SQLite inside your project. You get threaded replies, tag filtering, hover markers on annotated elements, and keyboard shortcuts. Works with Claude Code, Cursor, or any MCP-compatible agent that can read structured feedback and modify source files.
- tools
- 10
- auth
- Required
- transport
- STDIO
- env vars
- 2
- last updated
- Nov 6, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
get_review_summaryOverview of all pages with review counts.
Overview of all pages with review counts.
No parameter schema in public metadata yet.
get_reviewsList review comments. Optionally filtered by page. Shows status, tag, element context, and reply chains.
List review comments. Optionally filtered by page. Shows status, tag, element context, and reply chains.
No parameter schema in public metadata yet.
get_annotated_reviewsReturns only reviews that have element annotation metadata, including element name, CSS selector, full DOM path, selected text, and accessibility info.
Returns only reviews that have element annotation metadata, including element name, CSS selector, full DOM path, selected text, and accessibility info.
No parameter schema in public metadata yet.
get_pending_workAll open reviews grouped by page - the agent's "todo list".
All open reviews grouped by page - the agent's "todo list".
No parameter schema in public metadata yet.
add_reviewCreate a new review. Supports tags, annotation metadata (JSON), and threading via parent_id.
Create a new review. Supports tags, annotation metadata (JSON), and threading via parent_id.
No parameter schema in public metadata yet.
resolve_reviewMark a review as resolved. Sets resolved_at timestamp and resolved_by (defaults to "agent").
Mark a review as resolved. Sets resolved_at timestamp and resolved_by (defaults to "agent").
No parameter schema in public metadata yet.
reopen_reviewReopen a previously resolved review. Clears resolution info.
Reopen a previously resolved review. Clears resolution info.
No parameter schema in public metadata yet.
batch_resolveResolve all open reviews on a page at once.
Resolve all open reviews on a page at once.
No parameter schema in public metadata yet.
find_source_file_toolFind source files in PROJECT_ROOT matching a page ID. Searches by kebab-case, CamelCase, and glob patterns. Skips node_modules, dist, .git.
Find source files in PROJECT_ROOT matching a page ID. Searches by kebab-case, CamelCase, and glob patterns. Skips node_modules, dist, .git.
No parameter schema in public metadata yet.
get_setup_guideReturns the full setup guide (MCP config, REST API, browser UI).
Returns the full setup guide (MCP config, REST API, browser UI).
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
PROJECT_ROOT*Root directory of the project being reviewed
REVIEW_PORTHTTP port for REST API (default: 3200)
Readme
ui-ticket-mcp
Human-to-AI code review bridge. Review UI prototypes directly in the browser, then let AI agents read your feedback and fix the code automatically.
You click on elements, write review comments like "This button should be blue" or "The spacing is wrong here", and your AI coding agent (Claude Code, Codex, Cursor, etc.) picks them up via MCP and resolves them - with full context about which element you pointed at, its CSS, position, and surrounding DOM.
How it works
journey
title Using ui-ticket-mcp
section Review
Open your app in browser: 5: You
Click on a broken element: 4: You
Write what's wrong: 5: You
section AI resolves
Agent reads your feedback: 3: AI
Agent finds the source file: 4: AI
Agent fixes the code: 5: AI
Review disappears: 5: You, AI
One Python process handles everything - MCP protocol for the agent (stdio) and REST API for the browser UI (HTTP). Reviews are stored in a SQLite database inside your project.
Quick Start
1. Connect to your AI agent
Add to your project's .mcp.json (Claude Code, Codex, Cursor, etc.):
Details
- Repository
- github.com/0ics-srls/ui-ticket-mcp_public
- Category
- Web & Browser Automation
- Package
ui-ticket-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
More from 0ics-srls
Related Web & Browser Automation MCP servers
View all
Smsvirtualsms-io/mcp-serverReal SIM numbers for AI agents: SMS verification, rentals, proxies, cloud browser, x402 deposits.0stars
Helmdecktosin2013/helmdeckSelf-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent.6stars
Argusironclawdevs27/argusAutomated web QA via Chrome DevTools MCP — a11y, security, visual, env diff, CI; Aegis redaction.5stars
Pagerunner — The Browser Layer That Learnsenreign/pagerunnerReal Chrome profiles with site intelligence — already logged in, PII anonymization, sessions persist3stars
Anybrowsekc23go/anybrowseConverts any URL to clean, LLM-ready Markdown using real Chrome browsers3stars
anysitedwytmcl/anysite-mcpAny website as MCP tools: a real Chrome signed in as you, and shortcuts the agent saves as tools.1stars