tasks-mcp
Provides tools for managing tasks, projects, and courses in Notion databases, including retrieving pending tasks, creating tasks with due dates and priorities, and accessing active projects and courses.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tasks-mcp show my tasks for today"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tasks MCP is a Model Context Protocol (MCP) server that provides seamless integration with your Notion workspace for task management. It enables AI assistants to create, retrieve, and manage tasks, projects, and courses directly from your Notion databases.
NOTE: Tasks MCP is currently in active development. Features may evolve, and we're continually working to enhance the experience.
Features
With Tasks MCP, you can:
Retrieve Tasks: Get pending tasks filtered by time range (today, tomorrow, or this week) with "Not Started" status
Create Tasks: Add new tasks with title, due date, priority, and optional project/course associations
Manage Projects: Fetch active projects from your Notion workspace for task organization
Manage Courses: Access active courses to associate academic tasks
Smart Filtering: Automatically filters tasks based on status and time ranges
Rich Context: Tasks include associated project and course information for better context
Related MCP server: Obsidian Tasks MCP Server
Available Tools
The MCP server provides four main tools:
get-tasks
Fetches pending tasks from Notion based on time range filtering.
Parameters:
time_range(required) - One of "today", "tomorrow", or "week_from_today"Returns: List of tasks with title, due date, and associated project/course information
create-task
Creates a new task in your Notion Tasks database.
Parameters:
title(required) - Task descriptiondue_date(required) - ISO date format (YYYY-MM-DD)priority(required) - Integer 1-3 (1=highest, 3=lowest)project_id(optional) - Related project IDcourse_id(optional) - Related course ID
Returns: URL to the created task in Notion
get-projects
Fetches active projects from your Notion workspace.
Parameters: None
Returns: List of active projects with ID and title
get-courses
Fetches active courses from your Notion workspace.
Parameters: None
Returns: List of active courses with ID, title, and description
uv run python src/__main__.pyMotivation
Tasks MCP was created to bridge the gap between AI assistants and personal productivity systems. By providing direct access to Notion task databases through the Model Context Protocol, it enables AI assistants to understand your task context and help manage your workflow more effectively.
Technical Overview
Tasks MCP is built using modern Python technologies and follows MCP best practices:
MCP Framework: Built on the official MCP Python SDK for reliable protocol compliance
Notion Integration: Uses the official Notion API client for robust database interactions
Starlette Web Framework: Provides HTTP endpoints with CORS support and authentication
Authentication: Bearer token authentication for secure API access
Environment Configuration: Flexible configuration through environment variables and .env files
Error Handling: Comprehensive error handling with detailed logging
Data Source Management: Automatic retrieval of Notion database data source IDs
Setup
Environment Variables:
API_AUTH_TOKEN=your-api-auth-token NOTION_AUTH_TOKEN=your-notion-integration-token TASK_DATABASE=your-notion-tasks-database-id PROJECT_DATABASE=your-notion-projects-database-id COURSE_DATABASE=your-notion-courses-database-idInstallation:
uv syncRunning:
uv run python -m src --port 8000
Docker Deployment
Prerequisites
# Login to gcloud
gcloud auth login
# Configure Docker to use gcloud credentials for Artifact Registry
gcloud auth configure-docker us-west1-docker.pkg.devDeploy Steps
Build the image (for linux/amd64 since Cloud Run runs on Linux):
docker buildx build --platform linux/amd64 . -t tasks-mcpTag for Artifact Registry:
docker tag tasks-mcp:latest us-west1-docker.pkg.dev/stanford-mcp/stanford-mcp/tasks-mcp:latestPush to Artifact Registry:
docker push us-west1-docker.pkg.dev/stanford-mcp/stanford-mcp/tasks-mcp:latest
MCP Endpoint
The server is deployed and available at: https://tasks-mcp-280200773515.us-west1.run.app/mcp/
For MCP client configuration, use this endpoint with proper authentication headers.
Client Usage
For MCP Inspector
Use these headers when connecting to the MCP server:
{
"Authorization": "Bearer YJAna9RQePF@-uVw7_qBQt*apMF4*bZZfbTcybLobw*nGKCwteJMGh",
"Accept": "application/json, text/event-stream"
}For Claude Desktop
Add this configuration to your Claude Desktop claude_desktop_config.json:
"mcpServers": {
"stanford-mcp": {
"command": "npx",
"args": [
"mcp-remote",
"https://tasks-mcp-280200773515.us-west1.run.app/mcp/",
"--header", "Authorization: Bearer YJAna9RQePF@-uVw7_qBQt*apMF4*bZZfbTcybLobw*nGKCwteJMGh",
"--header", "Accept: application/json, text/event-stream"
]
}
},Made with 🫶 by @markmusic27
Available Tools
2 toolscreate-taskC
Creates a new task in my Notion Tasks database
Inputs: title (required), due_date (required), priority (required), body.
get-tasksC
Fetches tasks from my Notion based on filtering criteria
Inputs: time_range (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: get-tasks retrieves/filters tasks, while create-task creates a new task. There is no overlap or ambiguity in selecting between them.
Both names follow a consistent verb-noun hyphenated pattern (get-tasks, create-task). The only minor inconsistency is plural 'tasks' in get-tasks versus singular 'task' in create-task.
Two tools is thin for a task management server, even if the scope is limited to fetching and creating tasks. It is usable but lacks the breadth expected for the domain.
The surface covers creating and retrieving tasks, but lacks update, delete, complete, or status-change operations. These are notable gaps for a task management lifecycle.
Maintenance
Related MCP Connectors
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
Your planner in every AI chat: tasks, calendar, docs, habits, goals and memory, over MCP.
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables interaction with Notion workspaces, allowing users to search, query databases, create/update pages, and manage content via natural language through MCP.-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage Obsidian tasks with full CRUD operations, querying, and date-based filtering via MCP.5MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search, read, and query Notion workspaces, databases, and pages through an MCP gateway.329 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create, read, and manage tasks and projects in a personal todo system through MCP tools.1MIT