MCP.directory
ToolBartender

ToolBartender

sungminwoo0612

Converts natural language goals into structured, executable plans with step-by-step instructions and tool usage. Validates plans against available tools and generates execution prompts for AI agents.

Transforms goals into executable step-by-step plans.

180 views1Remote
developer toolsproductivity
GitHub

What it does

  • Parse natural language goals to extract intents and parameters
  • Generate step-by-step execution plans with tool sequences
  • Validate plans against available tool sets
  • Create execution prompts with safety rules and error handling
  • Explain plans in Korean with usage guidance

Best for

AI agent developers building goal-oriented systemsWorkflow automation with multi-step processesPlanning systems that need tool orchestration
Korean language supportBuilt-in plan validationSafety-focused execution prompts

About ToolBartender

ToolBartender is a community-built MCP server published by sungminwoo0612 that provides AI assistants with tools and capabilities via the Model Context Protocol. ToolBartender turns goals into clear, step-by-step action plans so you can execute faster and achieve results. It is categorized under developer tools, productivity. This server exposes 5 tools that AI clients can invoke during conversations and coding sessions.

How to install

You can install ToolBartender in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server supports remote connections over HTTP, so no local installation is required.

License

ToolBartender is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

Tools (5)

tb_parse_goal

자연어 goal에서 intent/slot(출발/도착/시간/날짜 등)을 추출합니다. (PlayMCP 친화: goal 문자열 1개 입력)

tb_plan_create

자연어 goal에서 실행 순서와 도구 호출 단계를 포함한 plan(JSON)을 생성합니다. available_tools를 제공하면 해당 도구만 사용하도록 제한합니다(엄격 모드).

tb_plan_validate

생성된 plan이 현재 available_tools로 실행 가능한지 검증합니다. available_tools가 비어 있으면 plan.steps에 포함된 도구 전체를 missing으로 반환합니다.

tb_plan_render_prompt

실행 에이전트/LLM이 plan을 안전하게 실행하도록 실행용 프롬프트를 생성합니다. 도구 사용 규칙, 실행 순서, 오류 대응, 사용자 확인 게이트를 포함합니다.

tb_plan_explain

plan을 사용자에게 한국어로 설명합니다: 어떤 도구를 왜 사용하는지, 필요한 확인 사항은 무엇인지 안내합니다.

ToolBartender 🍸

Python License: MIT CI Status Deploy (EC2)

Planner MCP that turns natural-language goals into safe, structured execution plans (JSON)

ToolBartender는 사용자의 자연어 요청을 하나의 goal로 받아,
어떤 MCP 도구를 어떤 순서로 호출해야 하는지 실행 계획(plan)을 생성하는 Planner MCP입니다.

실제 도구 실행은 하지 않고, LLM/실행 에이전트가 안전하고 예측 가능하게 실행하도록
steps / assumptions / required_confirmations / execution_hint를 포함한 JSON을 반환합니다.

한 줄 요약: ToolBartender = “도구 실행”이 아니라 “도구 조합 계획”을 만드는 MCP

PoC Endpoint

http://mcp.toolbartender.dev/mcp (Streamable HTTP / SSE)

Keywords

planner, safe execution, tool orchestration, PlayMCP

What it does

다음과 같은 복합 요청을 하나의 goal로 받아 plan을 생성합니다.

  • 이동 계획 (예: “오늘 오후 8시 판교에서 강남으로 이동”)
  • 일정 조회/조정
  • 정보 탐색 및 요약
  • 결과 전달(이메일/메신저 등)

Output Plan includes

  • steps: 사용할 MCP 도구 + 실행 순서
  • assumptions: 전제 조건
  • required_confirmations: 사용자 확인이 필요한 작업(특히 write 계열)
  • execution_hint: 실행 에이전트용 가이드

Exposed MCP tools (this server)

PlayMCP 등록 제약(정규식) 때문에 ToolBartender가 노출하는 tool name은 ASCII로 고정을 권장합니다.

  • plan_create : goal + available_tools → plan 생성
  • plan_validate: plan이 현재 컨텍스트(available_tools)에서 실행 가능한지 검증
  • plan_render_prompt: LLM 실행 에이전트가 steps를 “순서대로” 호출하도록 프롬프트 생성
  • plan_explain: 사용자에게 plan을 쉽게 설명

내부 plan.steps[*].tool_name은 다른 MCP들의 도구 이름이므로 (예: calendar.read, map.route) 그대로 두는 구조가 자연스럽습니다.

도구 I/O, 스키마, 예시는 docs/02_tools.md 참고.

Quickstart

1) Local run

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

python src/main.py
# Open http://localhost:3333/mcp in your browser

2) Inspector로 로컬 테스트

npx @modelcontextprotocol/inspector
# http://localhost:6274

Inspector UI에서 서버 URL을 http://localhost:3333/mcp로 연결합니다.

3) PlayMCP 통합 테스트

  • public URL 필요(ngrok/배포)
  • PlayMCP → “새로운 MCP 서버 등록” → https:///mcp 입력 → 임시 등록 → AI 채팅에 적용 흐름은 기존 README에 이미 있습니다.

Docs

  • docs/00_quickstart.md : 5분 셋업
  • docs/01_concept.md : Planner MCP 컨셉 / 철학 / 로드맵
  • docs/02_tools.md : tool별 입력/출력/예시 + naming 규칙
  • docs/03_playmcp.md : PlayMCP 등록 팁 / 심사 관점 체크리스트
  • docs/04_deploy.md : 배포(nginx/SSE 포함) + 도메인/Cloudflare 포인트
  • docs/05_troubleshooting.md : 405/핸드셰이크/SSE 관련 이슈 모음

License

MIT

Alternatives

Chrome DevTools MCP

Chrome DevTools MCP

chromedevtools
28.1k

AI-driven control of live Chrome via Chrome DevTools: browser automation, debugging, performance analysis and network mo

OfficialPopular
50711
Chrome DevTools

Chrome DevTools

chromedevtools
28.1k

Use Chrome DevTools for web site test speed, debugging, and performance analysis. The essential chrome developer tools f

OfficialPopular
3.9k172
GitHub

GitHub

github
27.6k

Extend your developer tools with GitHub MCP Server for advanced automation, supporting GitHub Student and student packag

OfficialRemotePopular
4.5k232
Task Master

Task Master

eyaltoledano
25.8k

Boost productivity with Task Master: an AI-powered tool for project management and agile development workflows, integrat

CommunityPopular
4.9k114

Related Skills

Browse all skills
ui-design-system

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.

18
ai-sdk

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

6
ai-assisted-development

Leveraging AI coding assistants and tools to boost development productivity, while maintaining oversight to ensure quality results.

4
api-documenter

Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals. Use PROACTIVELY for API documentation or developer portal creation.

4
teams-channel-post-writer

Creates educational Teams channel posts for internal knowledge sharing about Claude Code features, tools, and best practices. Applies when writing posts, announcements, or documentation to teach colleagues effective Claude Code usage, announce new features, share productivity tips, or document lessons learned. Provides templates, writing guidelines, and structured approaches emphasizing concrete examples, underlying principles, and connections to best practices like context engineering. Activates for content involving Teams posts, channel announcements, feature documentation, or tip sharing.

4
openai-knowledge

Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.

4