Scholarly MCP Server

What does “Scholarly” MCP Server do?

The Scholarly MCP Server is designed to connect AI assistants with a robust academic article search capability. By integrating with various scholarly vendors (with more to be added in the future), this server empowers developers to enhance their AI workflows by providing direct access to accurate and up-to-date scholarly articles. It acts as a bridge between AI agents and external academic data sources, enabling tasks such as searching for research papers, retrieving publication metadata, and sourcing relevant academic content. This tool is particularly beneficial for research assistants, educational platforms, and knowledge-centric applications that require seamless access to high-quality academic resources.

List of Prompts

No prompt templates were explicitly mentioned in the repository.

List of Resources

No resources were explicitly listed or described in the repository files.

List of Tools

No explicit tool definitions or entries (e.g., functions like search_articles, get_metadata, etc.) were found in the available repository structure or documentation. The repo is described as a “server to search for accurate academic articles,” so it likely includes a scholarly article search tool, but no concrete tool names or descriptions are present.

Use Cases of this MCP Server

• Academic Research Assistance
  Enables AI assistants to fetch scholarly articles for literature reviews or to support research queries, streamlining the research process for students and academics.
• Educational Content Enhancement
  Integrates with e-learning platforms to provide students with direct links to relevant, peer-reviewed articles, enriching course material with current research.
• Knowledge Base Expansion
  Supports the creation of dynamic knowledge bases by sourcing up-to-date academic articles, allowing organizations to maintain and expand their informational resources.
• Citation Generation
  Assists in generating citations and bibliographies by retrieving publication metadata for academic writing and referencing tasks.
• Fact-Checking and Verification
  Facilitates fact-checking by allowing AI agents to reference scholarly sources, improving the reliability and credibility of generated content.

How to set it up

Windsurf

1. Ensure you have the required prerequisites (e.g., Python, Docker, or Node.js as relevant).
2. Locate your Windsurf configuration file.
3. Add the Scholarly MCP Server by including the following JSON snippet in the mcpServers section:

   {
     "scholarly-mcp": {
       "command": "mcp-scholarly",
       "args": []
     }
   }
   

4. Save the configuration file and restart Windsurf.
5. Verify the server is running and accessible.

Claude

1. Make sure prerequisites (such as Python or Docker) are installed.
2. Open the Claude configuration file.
3. Add the Scholarly MCP Server under mcpServers:

   {
     "scholarly-mcp": {
       "command": "mcp-scholarly",
       "args": []
     }
   }
   

4. Save the file and restart Claude.
5. Confirm that the server is accessible from within Claude.

Cursor

1. Install necessary dependencies (Python, Docker, etc.).
2. Edit the Cursor configuration file.
3. Insert the following MCP server configuration:

   {
     "scholarly-mcp": {
       "command": "mcp-scholarly",
       "args": []
     }
   }
   

4. Save and restart Cursor.
5. Verify connection to the Scholarly MCP Server.

Cline

1. Confirm all prerequisites are met (Python, Node.js, etc.).
2. Access the Cline configuration file.
3. Add the Scholarly MCP Server:

   {
     "scholarly-mcp": {
       "command": "mcp-scholarly",
       "args": []
     }
   }
   

4. Save your changes and restart Cline.
5. Check that the server is running properly.

Securing API Keys

To secure API keys, use environment variables in your configuration. For example:

{
  "scholarly-mcp": {
    "command": "mcp-scholarly",
    "env": {
      "API_KEY": "your_api_key_here"
    },
    "inputs": {
      "api_key": "${API_KEY}"
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "scholarly-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “scholarly-mcp” to the actual name of your MCP server and replace the URL with your own MCP server URL.

Overview

Our opinion

Scholarly MCP Server provides a well-defined purpose and clear use cases, but documentation and repo content are sparse in terms of explicit prompt, resource, and tool definitions. Setup instructions can be inferred generically but are not detailed in the code. For a developer seeking plug-and-play academic search, it’s promising, but would benefit from richer documentation and explicit interface details.

MCP Score