Aṣṭādhyāyī MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ASHTADHYAYI_DATA_DIR | No | Data is stored in ASHTADHYAYI_DATA_DIR, or under $XDG_CACHE_HOME/ashtadhyayi-mcp (default ~/.cache/ashtadhyayi-mcp). To keep it local to your checkout, put --data-dir .data before the subcommand in every invocation. |
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": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_sutraB | Retrieve a sūtra and paginated source commentaries with provenance. |
| search_sutrasB | Literal lexical search of sūtra text and upstream word metadata. |
| get_sutra_contextC | Retrieve numeric neighbors and raw context metadata; no inference. |
| get_dhatuB | Exact dhātu lookup; returns all ambiguous matches with pagination. |
| search_dhatusC | Literal lexical search of upstream dhātu and meaning fields. |
| get_shabdaB | Retrieve śabda entries without dropping gender or lexical ambiguity. |
| search_shabdasC | Lexical search of the upstream śabda catalog and meanings. |
| get_dhatu_formsC | Retrieve stored finite and kṛdanta paradigms; paginate all sources. Missing forms do not imply invalidity. No generation or prefix composition. |
| get_shabda_formsB | Retrieve stored śabda paradigms with 24 case/number slots, alternatives and empty slots preserved. Vibhakti 8 means vocative. |
| lookup_formB | Reverse lookup of exact stored forms; returns all occurrences with pagination. Ambiguity is preserved. No sandhi analysis or grammatical validation. |
| get_form_coverageA | Report loaded form sources, omissions and unparsed groups; coverage is never exhaustive of Sanskrit. |
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 11 tools
Each tool targets a distinct retrieval mode: exact entity, lexical search, context, stored forms, reverse lookup, or coverage. The descriptions carefully separate similar-sounding operations, leaving no meaningful overlap.
Names follow a clear snake_case verb_noun convention: get_* for exact retrieval, search_* for lexical search, and lookup_form for reverse lookup. The one deviation is semantically justified and does not disrupt predictability.
With 11 tools, the server is well-scoped for its retrieval domain. Each tool covers a distinct facet without redundant operations or excessive fragmentation.
The surface covers sutras, dhatus, shabdas, stored paradigms, reverse form lookup, and coverage reporting, with explicit limitations acknowledged. No obvious retrieval operation is missing for the stated read-only Sanskrit grammatical domain.