π Semantic Scholar MCP Server
LocalAbout π Semantic Scholar MCP Server
Semantic Scholar MCP Server is a Python MCP server for the Semantic Scholar API. It is aimed at researchers and agents that need academic literature lookups, covering paper search, paper and author details, and citation data.
Key features
- 01Search papers on Semantic Scholar
- 02Retrieve detailed paper information
- 03Get author details
- 04Fetch citations and references for a paper
Use cases
- 01Letting an agent search papers by query string
- 02Mapping citations and references of a given paper
- 03Looking up details of a specific author
MCP support
This project is an MCP server that exposes paper search, detail lookup, and citation retrieval as tools for MCP clients.
Configuration
Local server config is the same for every client. Copy it into your clientβs MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEπ Semantic Scholar MCP Server
This project implements a Model Context Protocol (MCP) server for interacting with the Semantic Scholar API. It provides tools for searching papers, retrieving paper and author details, and fetching citations and references.
β¨ Features
- π Search for papers on Semantic Scholar
- π Retrieve detailed information about specific papers
- π€ Get author details
- π Fetch citations and references for a paper
π Prerequisites
- π Python 3.10+
- π
semanticscholarPython package - π§
mcpPython package (Model Context Protocol)
π Installation
Installing via Smithery
To install semanticscholar Server for Claude Desktop automatically via Smithery:
claude
npx -y @smithery/cli@latest install @JackKuo666/semanticscholar-mcp-server --client claude --config "{}"
Cursor
Paste the following into Settings β Cursor Settings β MCP β Add new server:
- Mac/Linux
npx -y @smithery/cli@latest run @JackKuo666/semanticscholar-mcp-server --client cursor --config "{}"
Windsurf
npx -y @smithery/cli@latest install @JackKuo666/semanticscholar-mcp-server --client windsurf --config "{}"
CLine
npx -y @smithery/cli@latest install @JackKuo666/semanticscholar-mcp-server --client cline --config "{}"
-
Clone this repository:
git clone https://github.com/JackKuo666/semanticscholar-MCP-Server.git cd semanticscholar-mcp-server -
Install the required packages:
pip install semanticscholar mcp
π₯οΈ Usage
-
Start the Semantic Scholar MCP server:
python semantic_scholar_server.py -
The server will start and listen for MCP requests.
-
Use an MCP client to interact with the server and access the following tools:
- π
search_semantic_scholar: Search for papers using a query string - π
get_semantic_scholar_paper_details: Get details of a specific paper - π€
get_semantic_scholar_author_details: Get details of a specific author - π
get_semantic_scholar_citations_and_references: Get citations and references for a paper
- π
Usage with Claude Desktop
Add this configuration to your claude_desktop_config.json:
(Mac OS)
{
"mcpServers": {
"semanticscholar": {
"command": "python",
"args": ["-m", "semanticscholar_mcp_server"]
}
}
}
(Windows version):
{
"mcpServers": {
"semanticscholar": {
"command": "C:\\Users\\YOUR\\PATH\\miniconda3\\envs\\mcp_server\\python.exe",
"args": [
"D:\\code\\YOUR\\PATH\\semanticscholar-MCP-Server\\semanticscholar_server.py"
],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}
Using with Cline
{
"mcpServers": {
"semanticscholar": {
"command": "bash",
"args": [
"-c",
"source /home/YOUR/PATH/.venv/bin/activate && python /home/YOUR/PATH/semanticscholar_mcp_server.py"
],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}
π File Structure
- π
semantic_scholar_search.py: Contains functions for interacting with the Semantic Scholar API - π₯οΈ
semantic_scholar_server.py: Implements the MCP server and defines the available tools
π€ Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
π License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.