Academic

Queries multiple academic data providers from MCP-enabled AI tools to fetch scholarly content.

python

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "xinsyousuozhi-academic-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/academic-mcp",
        "run",
        "academic-mcp"
      ],
      "env": {
        "LOSI_API_KEY": "YOUR_LOSI_KEY",
        "CINII_API_KEY": "YOUR_CINII_KEY",
        "HISTORY_API_KEY": "YOUR_HISTORY_KEY",
        "ENABLED_PROVIDERS": "kci,oak,kostma,losi,cinii,hgis,nl,eyis,nlir",
        "DATA_GO_KR_API_KEY": "YOUR_DATA_GO_KR_KEY"
      }
    }
  }
}

This MCP server lets you search Academic databases from AI tools that support the Model Context Protocol. It enables seamless querying of Korean and Japanese scholarly sources through MCP-enabled clients like Claude Desktop, Cursor, and Windsurf, expanding what your AI workflows can access.

How to use

You run the MCP server locally and connect your MCP-enabled client to it. Start the server, then configure your client with the provided MCP server entry so your AI tool can query the supported providers. Once connected, your AI conversations can retrieve academic articles, legal texts, historical data, and more depending on the active providers.

How to install

# Prerequisites: ensure you have Git and Python tooling available on your system

# 1) Clone the MCP server repository
git clone https://github.com/xinsyousuozhi/academic-mcp.git
cd academic-mcp

# 2) Install dependencies and prepare the runtime
uv sync

# 3) Set up environment variables (optional providers and API keys)
cp .env.example .env
# Edit .env to enable providers and add API keys as needed

# 4) Start the MCP as a local stdio server
# The server is run via uv with directory and run command as shown below
uv --directory /path/to/academic-mcp run academic-mcp

# 5) Start the client (Claude Desktop, Cursor, Windsurf, etc.) and point it to the MCP entry
# Use the provided configuration snippet to connect to the local server

Note: The exact path to the MCP directory should reflect where you cloned the repository and where the running entry point resides.}

## Configuration and usage notes

Configuration options are exposed through environment variables. You can enable specific providers and supply API keys as needed. Default behavior allows non-key providers to run without keys, while providers that require an API key will need you to insert the corresponding value.

## Environment and providers

Environment variables shown in the setup enable or disable specific data sources and provide authentication where required.

Built by

VeilStrat

AI signals for GTM teams