DeltaTask MCP Server
Provides API access to a locally-hosted task management system with features for creating, updating, and organizing tasks, including support for urgency levels, effort estimates, subtasks, and bi-directional sync with Obsidian markdown files.
brysontang
Tools
get_task_by_id
Get details for a specific task by ID.
search_tasks
Search tasks by title, description, or tags.
create_task
Create a new task.
update_task
Update an existing task.
delete_task
Delete a task.
sync_tasks
Sync tasks from Obsidian markdown into SQLite.
list_tasks
List all tasks with optional tags, if you user asks for a tag, please provide it in the request.
get_statistics
Get task statistics including completion rates and urgency distribution.
create_subtasks
Create multiple subtasks for a parent task with categories.
get_all_tags
Get all unique tag names used in tasks.
get_subtasks
Get subtasks for a given parent task ID.
finish_task
Mark a task as completed.
README
DeltaTask - Advanced Task Management System
A powerful, locally-hosted task management application with Obsidian integration and a Model Context Protocol (MCP) server.
Features
- Smart Task Management: Create tasks with urgency levels and effort estimates
- Prioritization Engine: Automatically sorts tasks by urgency and effort
- Task Decomposition: Split larger tasks into manageable subtasks
- Tagging System: Organize tasks with custom tags
- Local Storage: All data stored locally in SQLite database
- Obsidian Integration: Bi-directional sync with Obsidian markdown files
- MCP Server: Full API access through Model Context Protocol
Technical Details
Data Model
- Tasks: Core task entity with properties:
- Title and description
- Urgency (1-5 scale, 5 being highest)
- Effort (1-21 scale, following Fibonacci sequence)
- Completion status
- Parent-child relationships for subtasks
- Tags for categorization
Database Schema
The application uses SQLite with the following tables:
todos
: Stores all task items and their propertiestags
: Stores unique tag namestodo_tags
: Junction table for many-to-many relationship between tasks and tags
Obsidian Integration
DeltaTask creates and maintains a structured Obsidian vault:
- Task files with frontmatter metadata
- Tag-based views for filtering tasks
- Statistics dashboard
- Bi-directional sync between Obsidian markdown and SQLite database
MCP API Endpoints
The MCP server exposes the following operations:
get_task_by_id
: Get a specific task by IDsearch_tasks
: Find tasks by title, description, or tagscreate_task
: Create a new taskupdate_task
: Update a task's propertiesdelete_task
: Remove a tasksync_tasks
: Sync tasks from Obsidian markdown into SQLitelist_tasks
: List all tasksget_statistics
: Retrieve metrics about taskscreate_subtasks
: Split a task into multiple subtasksget_all_tags
: Get all unique tag namesget_subtasks
: Get subtasks for a given parent taskfinish_task
: Mark a task as completed
Getting Started
Prerequisites
- Python 3.10+
- SQLite3
- Obsidian (optional, for markdown integration)
Installation
-
Clone this repository
-
Set up the Python environment using
uv
:# Create and activate the virtual environment uv venv source .venv/bin/activate # On Windows: .venv\Scripts\activate # Install dependencies uv pip install -r requirements.txt
Running the MCP Server
The DeltaTask MCP server can be used with Claude for Desktop:
-
Configure Claude for Desktop:
- Open or create
~/Library/Application Support/Claude/claude_desktop_config.json
- Add the DeltaTask server configuration:
{ "mcpServers": { "deltatask": { "command": "uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/DeltaTask", "run", "server.py" ] } } }
- Restart Claude for Desktop
- Open or create
If you run into issues or want more details, check out the Docs for the MCP.
For instance from the docs:
You may need to put the full path to the uv
executable in the command
field. You can get this by running which uv
on MacOS/Linux or where uv
on Windows.
- Use the DeltaTask tools in Claude for Desktop by clicking the hammer icon
Model Context Protocol (MCP)
This application implements a Model Context Protocol approach for task management:
- Structured Data Model: Clearly defined schema for tasks with relationships
- Priority Calculation: Intelligent sorting based on multiple factors
- Hierarchical Organization: Parent-child relationships for task decomposition
- Tagging System: Flexible categorization for better context
- Statistics and Insights: Data aggregation for understanding task patterns
- Obsidian Integration: Markdown-based visualization and editing
License
MIT License
Recommended Servers
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.
Excel MCP Server
A Model Context Protocol server that enables AI assistants to read from and write to Microsoft Excel files, supporting formats like xlsx, xlsm, xltx, and xltm.
Playwright MCP Server
Provides a server utilizing Model Context Protocol to enable human-like browser automation with Playwright, allowing control over browser actions such as navigation, element interaction, and scrolling.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
Apple MCP Server
Enables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
DuckDuckGo MCP Server
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.

Supabase MCP Server
A Model Context Protocol (MCP) server that provides programmatic access to the Supabase Management API. This server allows AI models and other clients to manage Supabase projects and organizations through a standardized interface.
YouTube Transcript MCP Server
This server retrieves transcripts for given YouTube video URLs, enabling integration with Goose CLI or Goose Desktop for transcript extraction and processing.
MCP DuckDB Knowledge Graph Memory Server
A memory server for Claude that stores and retrieves knowledge graph data in DuckDB, enhancing performance and query capabilities for conversations with persistent user information.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.