BeautySpark
io.github.ThomasFindlay/beautyspark-mcp · v1.0.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
BeautySpark MCP server for ChatGPT, Claude and other MCP clients
Source: https://github.com/ThomasFindlay/beautyspark
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 22 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_my_look). Require confirmation before the agent calls them. |
What was checked
- https://mcp.beautyspark.me/mcp: answers without auth
Public tools: search_guides, get_guide, search, fetch, get_color_season, get_product_picks, check_product_for_season, find_article_looks, get_article_look, search_my_looks, get_my_look, save_my_look, update_my_look, delete_my_look, save_generation_to_my_looks, get_my_profile, list_my_palettes, list_my_generations, try_look_from_photo, confirm_look_generation, get_look_status, create_upload_url
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-thomasfindlay-beautyspark-mcp-41cbe2bf)