Scholar Feed
io.github.YGao2005/scholar-feed-mcp · v3.20.0 · 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
Rank CS/AI/ML papers by citations, forecast impact, or code adoption; trace 23.2M citation edges.
Source: https://github.com/YGao2005/scholar-feed-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 27 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (remove_from_collection, delete_watch). Require confirmation before the agent calls them. |
What was checked
- https://mcp.scholarfeed.org/mcp?src=…: answers without auth
- npm: scholar-feed-mcp@3.20.0 (static checks only; code not executed)
Public tools: search_papers, get_paper, get_citations, fetch_fulltext, find_author, co_author_graph, embed_text, get_field_orientation, get_foundational_lineage, save_paper, unsave_paper, like_paper, list_library, list_collections, create_collection, add_to_collection, remove_from_collection, create_watch, list_watches, check_watches, delete_watch, update_watch, preview_watch, find_gaps, ask_library, annotate_paper, check_drift
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-ygao2005-scholar-feed-mcp-7c68527d)