ui-ticket-mcp runs on your own machine — the client starts it, so there is no endpoint to ping. 199 installs a week from pypi. Last commit 28 Sep 2026.
Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ui-ticket-mcp -e 'PROJECT_ROOT=<PROJECT_ROOT>' -- uvx ui-ticket-mcp{
"mcpServers": {
"ui-ticket-mcp": {
"command": "uvx",
"args": [
"ui-ticket-mcp"
],
"env": {
"PROJECT_ROOT": "<PROJECT_ROOT>"
}
}
}
}[mcp_servers.ui-ticket-mcp]
command = "uvx"
args = ["ui-ticket-mcp"]
env = { PROJECT_ROOT = "<PROJECT_ROOT>" }{
"mcpServers": {
"ui-ticket-mcp": {
"command": "uvx",
"args": [
"ui-ticket-mcp"
],
"env": {
"PROJECT_ROOT": "<PROJECT_ROOT>"
}
}
}
}{
"servers": {
"ui-ticket-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"ui-ticket-mcp"
],
"env": {
"PROJECT_ROOT": "<PROJECT_ROOT>"
}
}
}
}Put your own value in place of
<PROJECT_ROOT> (Root directory of the project being reviewed).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
REVIEW_PORT (HTTP port for REST API (default: 3200)).
Alternatives to ui-ticket-mcp
same job, measured the same wayUser story map + kanban with a live browser UI; AI agents and humans plan the same backlog via MCP.
Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions
Let AI agents drive VS Code's built-in browser alongside you, with click-to-source.
Code-aware browser testing agent — 14 Playwright tools for AI code editors via MCP
Real-browser UI checks and speed audits for coding agents, catching fixes that only hide the bug.
AI-native browser runtime for autonomous agents with human-in-the-loop supervision
QA agent for vibecoded apps. Real browser checks, your AI fixes them. Ship to green.
Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.
ui-ticket-mcp — questions
Answers built from our own checks of this server.