Semantic Scholar

Provides local access to 200M+ Semantic Scholar papers via a Claude MCP client with search and retrieval endpoints.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "smaniches-semantic-scholar-mcp": {
      "command": "python",
      "args": [
        "-m",
        "semantic_scholar_mcp"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

This MCP server runs locally to give Claude Desktop and other MCP clients direct access to Semantic Scholar’s vast academic paper collection, enabling advanced search, paper details, author profiles, and recommendations without leaving your machine.

How to use

You will run the MCP server locally and connect your MCP client to it using a standard local process. The server exposes a set of tools that let you search papers, retrieve detailed information about a specific paper, find authors, view author profiles, get AI-powered recommendations, bulk retrieve multiple papers, and check the server health. Start the server with the documented command, then point your MCP client to the local process. Your API key remains on your machine and is provided to the server either via environment variables or per-request overrides.

How to install

Prerequisites: you need Python installed on your machine and access to the internet to install dependencies.

# Option 1: From source (recommended for development or customization)
git clone https://github.com/smaniches/semantic-scholar-mcp.git
cd semantic-scholar-mcp
pip install -e .

# Option 2: Claude Code flow (for Claude integration)
# First install the package:
pip install -e .

# Then register with Claude Code:
claude mcp add semantic-scholar -- python -m semantic_scholar_mcp

Additional steps and notes

The server is designed to run locally so your API key stays on your machine. Use the configuration options below to set your API key and start the MCP server.

Configuration and startup

Configure the server to use your Semantic Scholar API key and run it as a local process.

API key setup example

You can provide your API key either via an environment variable or by passing it per request.

Configuration example

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "python",
      "args": ["-m", "semantic_scholar_mcp"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "your-api-key-here"
      }
    }
  }
}

Security and best practices

Your API key should not be committed to source control. Store it as an environment variable and prefer using the environment method for persistent use.

Available tools

semantic_scholar_search_papers

Search papers with advanced filters such as year, fields of study, publication types, and citation count to refine results.

semantic_scholar_get_paper

Fetch detailed information for a specific paper, with options to include citations and references.

semantic_scholar_search_authors

Search for authors by name and retrieve matching author profiles.

semantic_scholar_get_author

Get an author's profile along with their publications and optional details.

semantic_scholar_recommendations

Obtain AI-powered paper recommendations based on a seed paper.

semantic_scholar_bulk_papers

Retrieve multiple papers in a single request, up to a specified limit.

semantic_scholar_status

Check server health and connectivity status of the Semantic Scholar API.