📌Overview

Purpose: The Semantic Scholar MCP server facilitates seamless integration with the Semantic Scholar API for enhanced research capabilities.

Overview: This framework, built with the mcp-python-sdk, allows users to deploy a server that communicates with the Semantic Scholar API. It aims to improve the accessibility and functionality of academic resources, ensuring higher efficiency in scholarly research.

Key Features:

API Integration: Easily connects to the Semantic Scholar API, enabling users to fetch a wide array of academic data and insights.
Custom Commands Configuration: Offers flexibility in server configuration through commands and environment variable settings, allowing for optimized usage based on user environment and requirements.

Semantic Scholar API MCP Server

Made with mcp-python-sdk

Important:
If you are still using the FastMCP version of this MCP server, please update to newer versions as FastMCP is deprecated.

Usage

Requirements:

pip install -r requirements.txt

Initialize the server:

mcp dev path/to/semantic-scholar-plugin.py

Install to Claude or add the following to claude/cline config:

"semantic-scholar": {
  "command": "uv",
  "args": [
    "run",
    "--with",
    "mcp",
    "mcp",
    "run",
    "/path/to/semantic-scholar-plugin.py"
  ]
}

Note:
Using uv with mcp may break certain Linux/macOS versions of Claude-desktop. You might need to set the command as:

"semantic-scholar": {
  "command": "/path/to/mcp",
  "args": [
    "run",
    "/path/to/semantic-scholar-plugin.py"
  ]
}

The path /path/to/mcp can be found by running which mcp in the terminal.

API Key

To use the Semantic Scholar API with higher rate limits, set your API key as an environment variable:

export SEMANTIC_SCHOLAR_API_KEY="your_api_key"

Or add an env key in MCP settings:

"semantic-scholar": {
  "command": "...",
  "args": "...",
  "env": {
    "SEMANTIC_SCHOLAR_API_KEY": "your_api_key"
  }
}

You can get an API key by filling out the form at: https://www.semanticscholar.org/product/api

Suggested Agent System Prompt

See: the AI pre-research agent that can make full use of this MCP server.

Known Issues