Server facts
huggingface-daily-paper-mcp
Project
- Author
- huangxinping
- License
- Not specified
- Category
- AI Models & Agents
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 7
- Last commit
- Data as of
Tags
- huggingface
- paper
Overview
HuggingFace paper discovery is organized around date selection in huggingface-daily-paper-mcp. The get_today_papers and get_yesterday_papers tools retrieve the corresponding daily listings, while get_papers_by_date accepts a date in YYYY-MM-DD format. This lets researchers request a particular day's papers rather than limiting retrieval to the current listing. Alongside these tool calls, MCP resources expose today's and yesterday's paper data as JSON, giving clients another interface to the same daily material.
Paper records include titles and abstracts, with author information supplemented through ArXiv integration to obtain complete author lists. Tags, vote counts, and submitter details provide additional context for each entry. Links point to the paper page and its PDF, connecting the retrieved metadata with the source material. The Python project communicates over stdio and documents client configuration for Claude Code, Cursor, Windsurf, and VS Code with Continue. Its repository also includes scraper code and MCP server tests.
huggingface-daily-paper-mcp setup notes
- huggingface-daily-paper-mcp records stdio only; confirm a network transport upstream before planning remote access.
- huggingface-daily-paper-mcp has no recorded license; confirm reuse terms in its repository.