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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。