shayari-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SHAYARI_CORPUS | No | Path to the generated corpus directory. Set this if the generated corpus lives outside the default `corpus/generated` directory. | corpus/generated |
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 |
|---|---|
| search_shayariB | Search active, owner-authorized Hindi Devanagari shayari text. |
| search_research_shayariB | Search source-valid but non-active research records. |
| get_shayariA | Get one active Hindi-facing shayari record by stable ID. |
| audit_corpusA | Return verified corpus counts and provenance metadata. |
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 distinctly scoped purpose: search active shayari, search research records, retrieve an active shayari by ID, and audit corpus metadata. No overlapping or ambiguous boundaries between tools.
All tools follow a consistent verb_noun snake_case pattern: search_shayari, search_research_shayari, get_shayari, audit_corpus. The naming uniformly uses clear verbs and nouns with no mixed conventions.
Four tools is well-scoped for a shayari corpus server, covering search (active and research), retrieval by ID, and audit. Each tool earns its place without redundancy or bloat.
The surface covers core search and retrieval for active shayari, plus audit metadata. However, there is no get_research_shayari by ID, meaning research records cannot be individually retrieved, leaving a minor gap for that workflow.