TablaFocusMCP
Unifies glossary lookup, composition design and validation, certification preparation, practice planning, and taal explanation for tabla learning into a single MCP interface.
README
TablaFocusMCP
TablaFocusMCP is a MCP server focused on tabla learning workflows. It unifies glossary lookup, composition design and validation, certification preparation, practice planning, and taal explanation into one consistent interface for AI assistants and serious learners. Alongside tools, it also exposes MCP resources (readable datasets) and prompts (guided workflows).
<p align="center"> <img src="assets/tablafocus-mcp-icon.png" alt="TablaFocusMCP icon" width="420" /> </p>
How To Use
Once tablafocus is installed in your MCP client, chat naturally about what you want to practice or build.
The assistant can explain taals, generate compositions, create quizzes/mocks, and plan practice weeks.
Try prompts like these:
Explain teental for a beginner, including vibhag structure, sam, and khali.Generate a valid 1-cycle tihai in teental (chatusra) and show the beat-by-beat mapping.Create a weekly tabla practice plan for 45 minutes/day, 5 days/week, focused on clarity and layakari.Build a 15-question ABGMVM Madhyama Pratham mock test with answer key and short rationales.I have a tihai idea for teental. Help me refine it so it resolves cleanly to sam in 1 cycle.Transpose this teental tihai into rupak while preserving the structural feel as closely as possible.
Workflow prompt templates are also available:
| Prompt name | What it guides | Inputs |
|---|---|---|
cert_prep_plan |
Certification workflow (catalog -> mock -> plan) |
board, certification_level, days_per_week, minutes_per_day |
weekly_practice_reset |
Weekly reset workflow after missed sessions or fatigue | goals (semicolon-delimited), daily_minutes, days_per_week, optional missed_days, completed_minutes, fatigue |
exam_week_plan |
Focused 7-day exam prep workflow | board, certification_level, daily_minutes, optional weak_areas, fatigue |
missed_week_recovery |
Recovery workflow after a disrupted practice week | goals (semicolon-delimited), daily_minutes, days_per_week, optional missed_days, completed_minutes, fatigue |
composition_polish |
Iterative composition draft -> validate -> refine flow | taal, form, jati, optional cycles, optional polish_rounds |
Core Tools
All tools return a common envelope with meta and data.
| Tool | What it does | Required inputs | Optional inputs | Output highlights |
|---|---|---|---|---|
glossary_lookup |
Finds glossary terms and definitions | None | term, category, limit (1-100) |
Matching entries, categories list, total matches |
compose_builder |
Builds mathematically valid compositions | taal, form, jati (tisra|chatusra|khanda|misra) |
cycles (1-12) |
Composition equation, parameters, timeline segments, alternatives |
composition_transposer |
Transposes a valid composition into a new taal/jati context | source (taal, form, jati, cycles, composition_input), target (taal, jati) |
target.cycles, preserve_mode=shape_ratio |
Chosen transposed composition, scale factor, preservation report, alternatives, warnings |
certification_catalog |
Lists certification tracks and level breakdowns | None | board, certification_level |
Board/level catalog with papers, categories, objectives, references |
assessment_builder |
Creates quizzes and certification mocks | mode (practice_quiz|cert_mock) |
count (1-100, default 10), seed, board, certification_level, taal |
Questions, answer key with rationale, rubric, optional certification reference |
practice_coach |
Generates adaptive weekly practice plans | goals (array), availability (object) |
profile_id, availability.daily_minutes (1-600), availability.weekly_minutes (1-4000), availability.days_per_week (1-7), week_context.missed_days (0-7), week_context.completed_minutes (0-4000), week_context.fatigue (low|medium|high) |
Weekly target, daily targets, per-day sessions, adaptive adjustments |
taal_catalog |
Returns full catalog or one taal detail | None | taal_id |
Taal structure, vibhag, sam/khali, clap-wave, counting guidance, theka |
composition_validator |
Validates composition equation and timeline checks | taal, form, jati, cycles (1-12), composition_input |
composition_input.P, G, M, g, optional detailed segments |
is_valid, failure reasons, equation/timeline/segment checks |
explain_taal |
Compatibility alias for taal explanation | taal |
None | Explanation payload sourced from canonical taal_catalog data |
How To Install
Run directly from npm:
npx -y tablafocus-mcp@latest
Codex CLI:
codex mcp add tablafocus -- npx -y tablafocus-mcp@latest
Claude Code:
claude mcp add -s user tablafocus -- npx -y tablafocus-mcp@latest
JSON-based clients (Claude Desktop, Cline, VS Code Copilot):
{
"mcpServers": {
"tablafocus": {
"command": "npx",
"args": ["-y", "tablafocus-mcp@latest"]
}
}
}
Cursor:
{
"name": "tablafocus",
"command": "npx",
"args": ["-y", "tablafocus-mcp@latest"]
}
Documentation
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.