ramayana-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAMAYANA_BOOK_DIR | No | Directory of a Ramayana_Book checkout used by `npm run build-index` to build the data/ directory (default: ../../ramayana-modernization/repo relative to this package). | ../../ramayana-modernization/repo |
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 | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_kandasA | List the seven kandas of the Ramayana with their Sanskrit names and chapter counts |
| get_verseA | Fetch a single verse by kanda, chapter (sarga) and verse number, with Sanskrit and available translations |
| get_sargaA | Fetch every verse of one sarga (chapter), with Sanskrit and available translations |
| search_versesA | Full-text search across Sanskrit and English/Hindi/Telugu translations; returns matching verse references with snippets |
| verse_of_the_dayA | A deterministic verse of the day: the same calendar date always yields the same verse, drawn uniformly from the whole corpus |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| kanda-index | Kanda names, Sanskrit titles and chapter/verse counts |
TDQS
Scored across 5 tools
Each tool targets a clearly distinct granularity of the same corpus: listing kandas, fetching one verse, fetching one sarga, full-text search, and a deterministic daily pick. verse_of_the_day vs get_verse could superficially touch the same data, but the descriptions make the boundaries obvious.
Four tools follow a clean verb_noun pattern (list_kandas, get_verse, get_sarga, search_verses) with consistent snake_case. verse_of_the_day breaks the pattern as a bare noun phrase with no verb, though it is still readable and unambiguous.
Five tools is well-scoped for a scripture-browsing server: structure listing, two retrieval granularities, search, and a novelty feature. No tool feels redundant or padded.
Core lifecycle for corpus navigation is covered: browse structure, fetch verse/chapter, search, and a daily highlight. A gap remains at the kanda level — there is no way to list the sargas belonging to a kanda, so agents must guess chapter numbers before calling get_sarga.