Skip to main content

Review system MCP server for UI prototypes. Humans write comments in browser, AI agents resolve them via MCP.

Project description

ui-ticket-mcp

Review system for UI prototypes. Humans write comments in the browser, AI agents resolve them via MCP. One process serves both MCP (stdio) and REST API (HTTP).

Setup

Add to your .mcp.json:

{
  "mcpServers": {
    "ui-ticket-mcp": {
      "command": "uvx",
      "args": ["ui-ticket-mcp"],
      "env": {
        "PROJECT_ROOT": "/path/to/your/project"
      }
    }
  }
}

uvx downloads and runs the package automatically. MCP connects via stdio, REST API starts in background on http://localhost:3200. Reviews are stored in {PROJECT_ROOT}/.reviews/reviews.db (auto-created, committable to git).

Port configurable via REVIEW_PORT env var.

Fallback if you don't have uv: pip install ui-ticket-mcp, then use "command": "ui-ticket-mcp" instead of uvx.

MCP Tools

Tool Description
get_review_summary() Summary of pages with open/resolved counts
get_reviews(page_id?) List comments, optionally filtered by page
add_review(page_id, author, text) Add a new comment
resolve_review(review_id, resolved_by?) Mark as resolved
reopen_review(review_id) Reopen a resolved review
batch_resolve(page_id, resolved_by?) Resolve all open on a page
get_pending_work() Open reviews grouped by page (todo list)
find_source_file_tool(page_id) Find source files matching a page_id
get_annotated_reviews(page_id?) Reviews with element annotation metadata
get_setup_guide() Full setup guide for the review system

REST API (starts automatically)

Method Endpoint Description
GET /api/reviews/summary Per-page summary
GET /api/reviews All reviews
GET /api/reviews/{page_id} Reviews for a page
POST /api/reviews/{page_id} Add review
PATCH /api/review/{id} Update status/text
DELETE /api/review/{id} Delete review
GET /api/version Server version

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ui_ticket_mcp-1.5.0.tar.gz (24.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ui_ticket_mcp-1.5.0-py3-none-any.whl (17.4 kB view details)

Uploaded Python 3

File details

Details for the file ui_ticket_mcp-1.5.0.tar.gz.

File metadata

  • Download URL: ui_ticket_mcp-1.5.0.tar.gz
  • Upload date:
  • Size: 24.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.12

File hashes

Hashes for ui_ticket_mcp-1.5.0.tar.gz
Algorithm Hash digest
SHA256 d3057415c79ce12ed178711f385197ed7635a936031e962775b4d0d001c2eb71
MD5 12827c63dfc47f6de4a281dbdf846177
BLAKE2b-256 5656e2ef77de59fb8f0a13cc6c0da9ed59bd651498674fe8b2eb9edf9b958dd2

See more details on using hashes here.

File details

Details for the file ui_ticket_mcp-1.5.0-py3-none-any.whl.

File metadata

  • Download URL: ui_ticket_mcp-1.5.0-py3-none-any.whl
  • Upload date:
  • Size: 17.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.12

File hashes

Hashes for ui_ticket_mcp-1.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c2c81e7933ec84b2085b62a04800041718170c69f8ea07026275b3eedb0eae15
MD5 99e5a1ecc100cec6c9b84241ca7254d8
BLAKE2b-256 3ba849a06a6eb445e176af73f8ab9ee0098e8c55d1c03ce4829294c743cf0674

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page