Semanticscholar MCP Server

This project implements a Model Context Protocol (MCP) server for interacting with the Semantic Scholar API. It provides tools for searching papers

Local serverstdioPython

What is the Semanticscholar MCP server?

Semanticscholar mcp server connects Semanticscholar to AI assistants that speak the Model Context Protocol. 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.

What Semanticscholar does

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.

Tools it exposes

Once connected, the assistant can call these 4 tools directly:

  • claude — The claude tool exposed by this server
  • Cursor — Paste the following into Settings → Cursor Settings → MCP → Add new server: - Mac/Linux s npx -y @smithery/cli@latest run
  • Windsurf — The Windsurf tool exposed by this server
  • CLine — 1. Clone this repository: git clone https://github.com/JackKuo666/semanticscholar-MCP-Server.git cd semanticscholar-mcp-server

Installing the semanticscholar mcp server

The server is distributed via npm as @smithery/cli, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Semanticscholar sits in that group, and the shape of its toolset — claude, Cursor, Windsurf among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • Maintained by JackKuo666, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the semanticscholar mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
claudeThe claude tool exposed by this server.
CursorPaste the following into Settings → Cursor Settings → MCP → Add new server: - Mac/Linux s npx -y @smithery/cli@latest run @JackKuo666/semanticscholar-mcp-server --client cursor --config "{}"
WindsurfThe Windsurf tool exposed by this server.
CLine1. Clone this repository: git clone https://github.com/JackKuo666/semanticscholar-MCP-Server.git cd semanticscholar-mcp-server

How to install the Semanticscholar MCP server

(Windows version):

```json
{
  "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": []
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Semanticscholar to claude.
  • Use Semanticscholar to Cursor.
  • Use Semanticscholar to Windsurf.

Frequently asked questions

It connects Semanticscholar to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (claude, Cursor, Windsurf, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Semanticscholar directly.