papers

cuentadesanti/papers

★ 0 stars Python 🔍 Search Updated today

Contextual-bandit paper recommender exposed as an MCP server. Thompson sampling + MMR over Semantic Scholar / arXiv / citation-graph ingestion.

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "papers": {
      "command": "uvx",
      "args": [
        "papers"
      ]
    }
  }
}

Or install with pip: pip install papers

README Excerpt

A contextual-bandit recommender for academic papers, exposed as a [Model Context Protocol](https://modelcontextprotocol.io) (MCP) server. Add papers, get personalized recommendations, give feedback, repeat. The longer you use it, the better it gets at finding things you actually want to read. It also ingests from real sources: keyword search across [Semantic Scholar](https://www.semanticscholar.org/) + [arXiv](https://arxiv.org/), DOI / arXiv-ID / title resolution, and citation-graph expansion.

Tools (2)

PAPERS_DATA_DIRS2_API_KEY

papers

Quick Install

README Excerpt

Tools (2)

Related Search Servers