Academic

Provides access to academic papers, ancient documents, and dictionaries from Korean and Japanese sources for AI-enabled search and retrieval.

python

GitHub Stars

python

Language

4 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": {
    "xinyousuozhi-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",
        "GUGAK_API_KEY": "your_gugak_key",
        "STDICT_API_KEY": "your_stdict_key",
        "HISTORY_API_KEY": "your_history_key",
        "FOLKENCY_API_KEY": "your_folkency_key",
        "ENABLED_PROVIDERS": "kci,oak,kostma",
        "TRIPITAKA_API_KEY": "your_tripitaka_key",
        "DATA_GO_KR_API_KEY": "your_data_go_kr_key"
      }
    }
  }
}

You can access Korean and Japanese academic databases through an MCP server, enabling AI tools to search scholarly papers, historical documents, and dictionaries efficiently. This server centralizes multiple providers and brings together diverse sources for your research workflows.

How to use

You connect your MCP-enabled AI tool to the Academic MCP server and start searches across supported providers. Use an MCP client to point to the local or remote MCP runtime, then issue your queries as you would with any search interface. The server gathers results from academic papers, ancient documents and history, and dictionaries, returning relevant records you can review or export.

How to install

# Step 1: clone the project
git clone https://github.com/xinsyousuozhi/academic-mcp.git

# Step 2: enter the project directory
cd academic-mcp

# Step 3: install or sync dependencies (library/runtime setup)
uv sync

# Step 4: prepare environment
cp .env.example .env
# Then you can add any needed API keys (providers that require keys)

{
  "mcpServers": {
    "academic_mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/academic-mcp",
        "run",
        "academic-mcp"
      ]
    }
  }
}

Additional content

Configuration notes and practical setup details enable you to tailor the server to your environment. The following sections outline how to enable providers, supply necessary API keys, and customize the runtime. When you start your client, ensure you’ve configured the MCP server as shown above so your AI tools can reach the integrated databases.

Environment and provider configuration

The server supports a range of data providers. You enable and customize them via environment variables. If a provider requires an API key, you must supply it; otherwise you can use the provider without a key. The environment variable section shows the keys you may set to activate specific providers.

Troubleshooting and notes

If searches fail or providers do not return results, verify that the MCP server process is running and accessible from your AI tool. Check the path in the runtime command and ensure firewall rules allow local or network access as needed. Confirm that any required API keys are present in your environment file and that the keys have not expired.

Built by

VeilStrat

AI signals for GTM teams