Semantic Scholar MCP server for AI agents

This MCP server bridges the gap between AI assistants and academic research by providing direct access to Semantic Scholar's comprehensive database. Whether you're conducting literature reviews, exploring citation networks, or seeking academic insights, this server offers a streamlined interface to millions of research papers.

Quick Overview

The Semantic Scholar MCP server enables:

Advanced paper discovery with smart search
AI-powered paper recommendations
Author research and profile retrieval
Citation analysis and reference mapping
Content discovery within papers

Installation Options

One-Click Install with Smithery

For Claude Desktop:

npx -y @smithery/cli@latest install @alperenkocyigit/semantic-scholar-graph-api --client claude --config "{}"

For Cursor IDE: Navigate to Settings → Cursor Settings → MCP → Add new server and paste:

npx -y @smithery/cli@latest run @alperenkocyigit/semantic-scholar-graph-api --client cursor --config "{}"

For Windsurf:

npx -y @smithery/cli@latest install @alperenkocyigit/semantic-scholar-graph-api --client windsurf --config "{}"

For Cline:

npx -y @smithery/cli@latest install @alperenkocyigit/semantic-scholar-graph-api --client cline --config "{}"

Manual Installation

Clone the repository:

git clone https://github.com/alperenkocyigit/semantic-scholar-graph-api.git
cd semantic-scholar-graph-api

Install dependencies:
```
pip install -r requirements.txt
```
Run the MCP Streamable HTTP server:
```
python server.py
```

Configuration Guide

Local Setups

Claude Desktop Setup

macOS/Linux Configuration: Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "semanticscholar": {
      "command": "python",
      "args": ["/path/to/your/semantic_scholar_server.py"]
    }
  }
}

Windows Configuration:

{
  "mcpServers": {
    "semanticscholar": {
      "command": "C:\\Users\\YOUR_USERNAME\\miniconda3\\envs\\mcp_server\\python.exe",
      "args": ["D:\\path\\to\\your\\semantic_scholar_server.py"],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

Cline Integration

{
  "mcpServers": {
    "semanticscholar": {
      "command": "bash",
      "args": [
        "-c",
        "source /path/to/your/.venv/bin/activate && python /path/to/your/semantic_scholar_server.py"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

Remote Setups

Auto Configuration

npx -y @smithery/cli@latest install @alperenkocyigit/semantic-scholar-graph-api --client <valid-client-name> --key <your-smithery-api-key>

Valid client names: [claude,cursor,vscode,boltai]

Available Tools

The server provides the following tools:

search_semantic_scholar - Search papers by query
search_semantic_scholar_authors - Find authors by name
get_semantic_scholar_paper_details - Get comprehensive paper info
get_semantic_scholar_author_details - Get author profiles
get_semantic_scholar_citations_and_references - Fetch citation network
get_semantic_scholar_paper_match - Find exact paper matches
get_semantic_scholar_paper_autocomplete - Get title suggestions
get_semantic_scholar_papers_batch - Bulk paper retrieval
get_semantic_scholar_authors_batch - Bulk author data
search_semantic_scholar_snippets - Search text content
get_semantic_scholar_paper_recommendations_from_lists - Get recommendations from positive/negative examples
get_semantic_scholar_paper_recommendations - Get recommendations from single paper

Usage Examples

Basic Paper Search

# Search for papers on machine learning
results = await search_semantic_scholar("machine learning", num_results=5)

Author Research

# Find authors working on natural language processing
authors = await search_semantic_scholar_authors("natural language processing")

Citation Analysis

# Get citation network for a specific paper
citations = await get_semantic_scholar_citations_and_references("paper_id_here")

AI-Powered Paper Recommendations

Multi-Example Recommendations

# Get recommendations based on multiple positive and negative examples
positive_papers = ["paper_id_1", "paper_id_2", "paper_id_3"]
negative_papers = ["bad_paper_id_1", "bad_paper_id_2"]
recommendations = await get_semantic_scholar_paper_recommendations_from_lists(
    positive_paper_ids=positive_papers,
    negative_paper_ids=negative_papers,
    limit=20
)

Single Paper Similarity

# Find papers similar to a specific research work
similar_papers = await get_semantic_scholar_paper_recommendations(
    paper_id="target_paper_id",
    limit=15
)

Content Discovery

# Search for specific text content within papers
snippets = await search_semantic_scholar_snippets(
    query="neural network optimization",
    limit=10
)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "semanticscholar" '{"command":"python","args":["/path/to/your/semantic_scholar_server.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "semanticscholar": {
            "command": "python",
            "args": [
                "/path/to/your/semantic_scholar_server.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "semanticscholar": {
            "command": "python",
            "args": [
                "/path/to/your/semantic_scholar_server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect