annotate_paper — Scholar Feed MCP Tool
annotate_paper
(annotate paper) is one of 27 tools on the
Scholar Feed
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call annotate_paper from your client
- Claude Code Scholar Feed annotate_paper run in your project directory
- Claude Desktop Scholar Feed annotate_paper ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Scholar Feed annotate_paper ~/.cursor/mcp.json
- VS Code Scholar Feed annotate_paper .vscode/mcp.json
- Zed Scholar Feed annotate_paper ~/.config/zed/settings.json
- Windsurf Scholar Feed annotate_paper ~/.codeium/windsurf/mcp_config.json
- Cline Scholar Feed annotate_paper ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Scholar Feed annotate_paper ~/.gemini/settings.json
- Grok Scholar Feed annotate_paper .mcp.json (in your project root)
- ChatGPT Scholar Feed annotate_paper Settings → Connectors → Advanced → Developer mode
- Claude.ai Scholar Feed annotate_paper Settings → Connectors → Add custom connector
- LangChain Scholar Feed annotate_paper pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http scholar-feed-mcp https://mcp.scholarfeed.org/mcp?src=mcp-registry
Other tools on this server
- 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
- check_drift
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.