Genji MCP Server

A Model Context Protocol (MCP) server that provides access to the Genji API for classical Japanese literature analysis and search. This server enables AI assistants like Claude to search and analyze texts from classical Japanese literature with advanced normalization features.

- 🏥Health Check: Monitor API status and availability
- 🔍Advanced Text Search: Search classical Japanese texts with sophisticated normalization options
- ⚙️Normalization Rules: Access and understand text normalization rules
- 🔍Normalization Preview: Preview how text will be normalized before processing
- 🇯🇵Classical Japanese Support: Specialized handling of historical Japanese text variations

npm install -g @nakamura196/genji-mcp-server

Add the server to your Claude Desktop configuration file:

Edit~/Library/Application Support/Claude/claude_desktop_config.json:

{ "mcpServers": { "genji": { "command": "npx", "args": ["@nakamura196/genji-mcp-server"] } } }

Edit%APPDATA%/Claude/claude_desktop_config.json:

{ "mcpServers": { "genji": { "command": "npx", "args": ["@nakamura196/genji-mcp-server"] } } }

Alternatively, if you installed globally:

{ "mcpServers": { "genji": { "command": "genji-mcp-server" } } }

After configuration, restart Claude Desktop. The Genji tools will be automatically available. You can ask Claude for classical Japanese literature analysis like:

- "Check if the Genji API is working"
- "Is the classical Japanese literature database available?"

- "Search for '花' in classical Japanese texts"
- "Find passages containing '源氏' with phonetic normalization"
- "Search for text in volume 1 of Genji Monogatari"
- "Look for '恋' with all normalization options enabled"

- "What normalization rules are available for classical Japanese?"
- "Preview how '源氏物語' would be normalized"
- "Show me the normalization rules for historical kana"

Checks the health and availability of the Genji API.

Searches classical Japanese texts with advanced normalization options.

- query(string, optional): Search query text
- limit(number, optional): Maximum results to return (1-100, default: 20)
- offset(number, optional): Number of results to skip (default: 0)
- sort(string, optional): Sort order for results
- expand_repeat_marks(boolean, optional): Expand repeat marks (default: true)
- unify_kanji_kana(boolean, optional): Unify kanji/kana variations (default: true)
- unify_historical_kana(boolean, optional): Unify historical kana (default: true)
- unify_phonetic_changes(boolean, optional): Unify phonetic variations (default: true)
- unify_dakuon(boolean, optional): Unify voiced sound variations (default: true)
- vol_str(array, optional): Volume/chapter filter

Retrieves the list of available text normalization rules.

Previews how text would be normalized with current rules.

- text(string, required): Text to preview normalization for

The server supports various normalization options for classical Japanese text:

- Repeat Marks Expansion: Converts repeat marks (々, ゝ, ゞ) to full characters
- Kanji-Kana Unification: Handles variations between kanji and kana representations
- Historical Kana Unification: Normalizes historical kana usage to modern equivalents
- Phonetic Changes: Accounts for historical phonetic variations
- Dakuon Unification: Handles voiced/unvoiced sound variations

- Node.js 16.0.0 or higher
- Internet connection for API access
- Access to the Genji API (https://genji-api.aws.ldas.jp)

# Clone the repository git clone https://github.com/nakamura196/genji-mcp-server.git cd genji-mcp-server # Install dependencies npm install # Build the project npm run build # Start in development mode npm run dev

This server interfaces with theGenji API, which provides:

MIT License - see theLICENSEfile for details.

If you encounter any issues, please file them on theGitHub Issuespage.

- Genji API- The underlying API for classical Japanese literature
- Model Context Protocol- The protocol this server implements

An MCP server for advanced research assistance, configurable via environment variables.