Semantic Scholar MCP Server

A Model Context Protocol (MCP) server for searching and analyzing academic papers via the Semantic Scholar API.

Disclaimer: This project is not officially affiliated with, endorsed by, or sponsored by Semantic Scholar or the Allen Institute for AI.

Prerequisites

• Python 3.13+
• uv package manager

Quick Start

Claude Code

claude mcp add semantic-scholar -s user -- uvx --from git+https://github.com/akapet00/semantic-scholar-mcp semantic-scholar-mcp

Claude Desktop

Add to your config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/akapet00/semantic-scholar-mcp",
        "semantic-scholar-mcp"
      ]
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/akapet00/semantic-scholar-mcp",
        "semantic-scholar-mcp"
      ]
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/akapet00/semantic-scholar-mcp",
        "semantic-scholar-mcp"
      ]
    }
  }
}

OpenCode

Add to opencode.json:

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/akapet00/semantic-scholar-mcp",
        "semantic-scholar-mcp"
      ]
    }
  }
}

Other Clients

Any MCP-compatible client can use this server via stdio transport. Run the server with:

uvx --from git+https://github.com/akapet00/semantic-scholar-mcp semantic-scholar-mcp

API Key (Optional)

The server works without an API key. For higher rate limits, get a key at https://www.semanticscholar.org/product/api and pass it as an environment variable.

Claude Code:

claude mcp add semantic-scholar -s user -e SEMANTIC_SCHOLAR_API_KEY=your_key -- uvx --from git+https://github.com/akapet00/semantic-scholar-mcp semantic-scholar-mcp

Claude Desktop / Cursor / Windsurf / OpenCode — add an "env" block to the config:

"env": {
  "SEMANTIC_SCHOLAR_API_KEY": "your_key"
}

SSL Issues

If you’re behind a corporate proxy or firewall and see CERTIFICATE_VERIFY_FAILED errors, set DISABLE_SSL_VERIFY=true as an environment variable (same approach as the API key above). Only use this in trusted networks.

Why MCP?

The same prompt was run with and without this MCP server connected to Claude Code (Opus 4.6):

Find the first journal paper by Ante Kapetanovic and extract all references from that paper.

Without MCP, the agent spent most of its turns fighting HTTP errors, parsing raw HTML, and installing packages. With MCP, the author and paper were found in 2 turns. The same publisher restriction on references was hit, but recovery was faster and every reference was retrieved via a clean fallback.

Full analysis: ANALYSIS.md

Tools

Papers

Authors

Recommendations

Session & Export

Updating

When installed via git+https://..., updates are not pulled automatically. To get the latest version:

# Refresh the cached package
uvx --refresh --from git+https://github.com/akapet00/semantic-scholar-mcp semantic-scholar-mcp

# Or re-add in Claude Code
claude mcp remove semantic-scholar -s user
claude mcp add semantic-scholar -s user -- uvx --from git+https://github.com/akapet00/semantic-scholar-mcp semantic-scholar-mcp

You can also pin to a specific branch, tag, or commit:

uvx --from git+https://github.com/akapet00/[email protected] semantic-scholar-mcp

Development

git clone https://github.com/akapet00/semantic-scholar-mcp.git
cd semantic-scholar-mcp
uv sync

# Run tests
uv run pytest

# Run integration tests (requires network access)
uv run pytest -m integration

# Lint and format
uv run ruff check src/ tests/
uv run ruff format src/ tests/

# Type checking
uv run ty check src/

# Dev mode with inspector
uv run fastmcp dev src/semantic_scholar_mcp/server.py

Configuration

See CONFIGURATION.md for all environment variables (cache, retry, circuit breaker, logging, default limits).

See Also

• MCP vs. Skill: Zero-Context Alternative — a Claude Code skill that achieves comparable results for personal use with zero base context cost
• Building the Semantic Scholar MCP — design decisions and implementation walkthrough
• MCP vs. Vanilla Agent — the comparative analysis that motivated this project
• Scholar skill source — lightweight skill-based alternative for personal workflows

License

MIT