Genji MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| genji_health_checkB | Check the health status of the Genji API |
| genji_searchC | Search classical Japanese texts with advanced normalization options |
| genji_get_normalization_rulesB | Get the list of available text normalization rules |
| genji_preview_normalizationC | Preview how text would be normalized with current rules |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: getting rules, health checks, previewing normalization, and searching texts. The descriptions make it easy to differentiate between configuration, monitoring, testing, and core functionality.
All tools follow a consistent 'genji_verb_noun' pattern with snake_case throughout. The naming is predictable and readable, making it easy to understand each tool's function at a glance.
Four tools is well-scoped for a server focused on text normalization and search in classical Japanese texts. Each tool earns its place by covering distinct aspects: configuration, health, preview, and core search functionality.
The toolset covers the essential workflows for text normalization and search, but there are minor gaps such as updating or managing normalization rules beyond just getting them. However, agents can work effectively with the provided tools for most use cases.