Huggingface Daily Papers

Created By
huangxinping9 months ago
A MCP (Model Context Protocol) server for fetching HuggingFace daily papers.
Overview

what is Huggingface Daily Papers?

Huggingface Daily Papers is a Model Context Protocol (MCP) server designed to fetch daily research papers from HuggingFace.

how to use Huggingface Daily Papers?

To use the server, you can either run it directly using the command uvx huggingface-daily-paper-mcp or clone the repository for local development and run the server using Python.

key features of Huggingface Daily Papers?

  • Fetch today's, yesterday's, or specific date HuggingFace papers.
  • Provides detailed information including paper title, authors, abstract, tags, votes, and submission details.
  • Includes links to papers and PDF downloads.
  • Supports MCP tools and resource interfaces with ArXiv integration.
  • Comprehensive error handling and logging with complete test coverage.

use cases of Huggingface Daily Papers?

  1. Researchers can quickly access the latest papers in their field.
  2. Developers can integrate the server into their applications to provide users with up-to-date research.
  3. Educators can use the server to curate daily reading materials for students.

FAQ from Huggingface Daily Papers?

  • Can I fetch papers from any date?

Yes! You can fetch papers from today, yesterday, or any specific date by providing the date in YYYY-MM-DD format.

  • Is there a way to download the papers?

Yes! Each paper entry includes a PDF download link.

  • What programming language is used for this project?

The project is developed in Python 3.10+.

Server Config

{
  "mcpServers": {
    "huggingface-papers": {
      "command": "uvx",
      "args": [
        "huggingface-daily-paper-mcp"
      ]
    }
  }
}
Project Info
Created At
9 months ago
Updated At
9 months ago
Author Name
huangxinping
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

20 hours ago
Gpt Scrambler

2 days ago