Semantic Scholar

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.

python

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": {
    "zongmin-yu-semantic-scholar-fastmcp-mcp-server": {
      "command": "fastmcp",
      "args": [
        "run",
        "/path/to/your/semantic-scholar-server/run.py"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run the Semantic Scholar MCP Server as a local, configurable MCP endpoint that exposes paper, author, and citation data through a FastMCP bridge. This server handles authentication when you provide an API key, supports batch operations, and exposes a built-in HTTP bridge for quick workflows. Use it to power fast, programmatic access to semantic scholar data from your MCP client.

How to use

You will run the MCP server locally or in your environment and connect to it through an MCP client. The server offers a suite of endpoints for searching papers, retrieving paper and author details, exploring citation networks, and generating recommendations. If you provide a Semantic Scholar API key, you get higher rate limits and potentially better performance. The built‑in HTTP bridge exposes common workflows over a lightweight REST interface, so you can prototype and test queries quickly.

How to install

Prerequisites you need before installation:

Python 3.8+
FastMCP

Installation steps you will follow to run the server locally:

How to install

Clone the repository and enter the project directory.

git clone https://github.com/YUZongmin/semantic-scholar-fastmcp-mcp-server.git
cd semantic-scholar-server

How to install

Install FastMCP and other dependencies.

# Follow the dependency guidance from the FastMCP project
# Example placeholder if you follow a typical Python/CLI setup
python -m pip install -r requirements.txt

How to install

Configure FastMCP and the Semantic Scholar MCP Server in your environment. Use the example configuration to integrate with Claude Desktop or your MCP client.

{
  "mcps": {
    "Semantic Scholar Server": {
      "command": "/path/to/your/venv/bin/fastmcp",
      "args": [
        "run",
        "/path/to/your/semantic-scholar-server/run.py"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "your-api-key-here"  
      }
    }
  }
}

How to install

Start using the server from your MCP client. Claude Desktop will manage starting and stopping the server when needed.

Additional configuration and notes

Optional API key usage enables higher rate limits. If you do not provide an API key, the server will operate with unauthenticated access and lower rate limits.

Configuration

The server supports an internal HTTP bridge for common workflows. You can enable and configure the bridge with environment variables and run the bridge on a dedicated port. A representative bridge setup exposes endpoints such as paper search, paper details, batch lookups, author search, author details, and recommendations.

Troubleshooting and notes

If you encounter rate limit issues, verify whether you are using an API key and adjust your request patterns accordingly. The bridge reuses the HTTP utilities to maintain consistent rate limiting and connection pooling.

Examples of usage patterns

Basic usage includes searching papers with filters, retrieving detailed information for papers or authors, performing batch lookups, and requesting recommendations for single or multiple papers. The API supports field customization and paging where appropriate.

Available tools

paper_relevance_search

Search papers using relevance ranking with comprehensive query parameters, including year range and citation filters, returning paginated results with customizable fields.

paper_bulk_search

Bulk search with sorting options for large result sets, supporting sorting by citation count, publication date, and other criteria.

paper_title_search

Find papers by exact title match and retrieve detailed information with selectable fields.

paper_details

Get comprehensive details for a single paper, supporting multiple ID formats (S2, DOI, ArXiv, etc.) and nested field selection.

paper_batch_details

Efficiently retrieve details for up to 1000 papers in a single request with consistent field options.

paper_citations

Retrieve papers that cite a given paper, with pagination, optional context, and field customization.

paper_references

Retrieve papers referenced by a given paper, with pagination, optional context, and field customization.

author_search

Search for authors by name with paginated results and customizable fields.

author_details

Get detailed information about an author, including metrics like h-index and total citations.

author_papers

List papers authored by a specific researcher with pagination and sorting.

author_batch_details

Batch retrieve details for multiple authors in a single request.

paper_recommendations_single

Get recommendations for a single paper with customizable fields.

paper_recommendations_multi

Get recommendations based on multiple papers, supporting positive and negative exemplars.

Built by

VeilStrat

AI signals for GTM teams