
Routine
Connects to the Routine productivity app to access and manage your tasks, calendar events, documents, and contacts through AI assistants.
Creates and manages reusable workflows by capturing sequences of tool calls and converting them into parameterized routines that can be invoked by name for automating repetitive multi-step tasks.
What it does
- Access calendar events and schedules
- Retrieve task and project information
- Search and view document pages
- Look up contacts by email address
- Get user profile and account details
- View daily agenda and timeline
Best for
About Routine
Routine is a community-built MCP server published by mquan that provides AI assistants with tools and capabilities via the Model Context Protocol. Routine is workflow automation software that lets you create and manage automated approval and multi-step workflows to s It is categorized under productivity, developer tools.
How to install
You can install Routine 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 runs locally on your machine via the stdio transport.
License
Routine is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
MCP Routine
π π³βοΈπ°ππΌ MCP Routine is a MCP server that lets you create custom tools on the fly. It stitches actions executed by multiple MCP tools into a reusable routine.
Why?
If you perform the same sequence of tool calls over and over, a routine will save you time and remove prompting inconsistencies. A routine includes full context of the exact set of tools and inputs needed to execute a full task.
Installation
Copy the following into your MCP client's JSON file
{
"mcpServers": {
"myRoutines": {
"command": "npx",
"args": ["-y", "mcp-routine"],
"env": {
"FILENAME": "/path/to/your/mcp-routines.json"
}
}
}
}
How to use it?
- Perform your task by prompting AI to execute tools.
- Once the task is completed, instruct AI to create a new routine for your task.
- Refresh your MCP client to update the tools. Then use it to execute the same sequence of tools.
The MCP server includes the following tools to manage routines
create-routine
load-routines
update-routine
delete-routine
Examples
Research a topic, then write the result into a new page in a given folder.
**User**: "add an Onboarding page to the Getting started page
**AI**: I'll help you add an "Onboarding" page to the Getting Started page. First, I'll need to find the Getting Started page ID.
Let me search for it:
Great, I found the Getting Started page. Now I'll create a new "Onboarding" page under it:
I've successfully created a new page titled "Onboarding" under the Getting Started page. The page has been created with a basic title, and you can now access it at the URL provided in the response. Would you like me to add any specific content to this new Onboarding page?
**User**:Yes, add some placeholder information for a standard onboarding experience
**AI**: I'll add some structured placeholder content to the Onboarding page to outline a standard onboarding experience.
**User**: now convert all these steps into a route to insert a page into a parent page
**AI**: I'll create a routine that captures the steps we just performed to insert a page into a parent page with structured content. This will make it reusable for future similar tasks.
I've created a routine called insert_structured_page that captures the workflow we used. The routine has three main steps:
1. Search for the parent page using its title to get the page ID
2. Create a new page under the found parent page
3. Add structured content to the new page with sections and bullet points
The routine is parameterized so you can customize:
- parent_page_title: The title of the parent page to search for
- new_page_title: The title for the new page
- welcome_message: Introduction text for the page
- section1_title: Title for the first section (can add more sections as needed)
- bullet_point1, bullet_point2, bullet_point3: Bullet points under sections
- help_message: The help/support message at the bottom
To use this routine, you would just need to provide these parameters with your desired content, and it will create a structured page with consistent formatting.
Development
Build
npm run build
Execute
npx -y --prefix /path/to/local/mcp-routine routine
Publish
npm publish --access public
Alternatives
Related Skills
Browse all skillsUI 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.
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".
Leveraging AI coding assistants and tools to boost development productivity, while maintaining oversight to ensure quality results.
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.
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.
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`.