Skip to main content

MCP server for Semantic Scholar API integration with Claude Desktop

Project description

Semantic Scholar MCP Server

License: MIT Python 3.10+ MCP Compatible

Access millions of academic papers from Semantic Scholar using the Model Context Protocol (MCP). Works with Claude Code, Claude Desktop, and other MCP-compatible editors.

Features

33 comprehensive tools - Search papers, analyze citations, manage research
Smart AI prompts - Literature reviews and citation analysis
Project & memory management - Organize your research workflow
Fast & reliable - Built-in caching and error recovery
Free to use - No API key required (optional for higher limits)

Installation

One command (recommended):

claude mcp add semantic-scholar -- uvx semantic-scholar-mcp

Manual setup (add to MCP settings):

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": ["semantic-scholar-mcp"]
    }
  }
}

With API key (for higher rate limits):

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": ["semantic-scholar-mcp"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "your-api-key-here"
      }
    }
  }
}

Get your free API key at: https://www.semanticscholar.org/product/api

Quick Start

Ask in natural language:

"Find recent papers on transformer architectures"
"Show me details for paper DOI 10.1038/nature14539"
"Get recommendations based on the BERT paper"
"Create a literature review on quantum computing"
"Save this review to memory as 'quantum_survey'"

What You Can Do

📄 Paper Research

  • Search papers with advanced filters (year, citations, fields)
  • Get full details: abstracts, authors, citations, references
  • Convert PDFs to Markdown for analysis
  • Find related papers with AI recommendations

👤 Author Analysis

  • Search researchers by name or field
  • Get author profiles with h-index and metrics
  • List all publications by author
  • Batch operations for multiple authors

🧠 Smart Features

  • AI-powered paper recommendations
  • Semantic search with SPECTER embeddings
  • Citation network analysis
  • Research trend identification

💾 Research Organization

  • Create multiple research projects
  • Save literature reviews and notes
  • Manage research memories
  • Switch between project contexts

📊 Datasets

  • Access Semantic Scholar datasets
  • Download paper/author data
  • Get incremental updates

License

MIT License - see LICENSE for details.

⚠️ The get_paper_fulltext tool uses PyMuPDF4LLM (AGPL licensed). Commercial usage may require a commercial PyMuPDF license.

Acknowledgments

  • Semantic Scholar for the academic graph API
  • Anthropic for the MCP specification
  • The academic community for making research accessible

Built for researchers worldwide 🌍

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

semantic_scholar_mcp-0.4.0.tar.gz (370.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

semantic_scholar_mcp-0.4.0-py3-none-any.whl (124.0 kB view details)

Uploaded Python 3

File details

Details for the file semantic_scholar_mcp-0.4.0.tar.gz.

File metadata

  • Download URL: semantic_scholar_mcp-0.4.0.tar.gz
  • Upload date:
  • Size: 370.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for semantic_scholar_mcp-0.4.0.tar.gz
Algorithm Hash digest
SHA256 43907ca1f38b4326269e40ee470d247418be5fac49c54fe14c561ddbf6a50d59
MD5 7a2910668579f03f113ee8a8a00533ef
BLAKE2b-256 58cdc1efcccdc784defc09667efcbed21f627e8aa57a8c36ed88f88d3ec3f5c5

See more details on using hashes here.

Provenance

The following attestation bundles were made for semantic_scholar_mcp-0.4.0.tar.gz:

Publisher: release.yml on hy20191108/semantic-scholar-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file semantic_scholar_mcp-0.4.0-py3-none-any.whl.

File metadata

File hashes

Hashes for semantic_scholar_mcp-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2d25ab3eea8fc5e8091a35888dd92521bb86a73e7bc089682a74af2ee3d3bfcd
MD5 03bdf8a15682b56a7c7ff741e28bcf32
BLAKE2b-256 ff48d863510b59f023717e8adab2d299eb7a6c45e51dacc83bc0536a3c8cd9f4

See more details on using hashes here.

Provenance

The following attestation bundles were made for semantic_scholar_mcp-0.4.0-py3-none-any.whl:

Publisher: release.yml on hy20191108/semantic-scholar-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page