What are the runtime requirements?
Python 3.10+ and SQLite3 are required. Obsidian is optional for markdown integration.
@brysontang
Basic information
A powerful MCP (Model Context Protocol) server for Claude Desktop, integrating task management, SQLite, and Obsidian visualization.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"deltatask": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/DeltaTask",
"run",
"server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
DeltaTask is a locally-hosted task management application with a Model Context Protocol (MCP) server. It integrates with Obsidian for bi-directional markdown sync and stores all data in a local SQLite database. Designed for power users, it offers smart task creation, automatic prioritization, decomposition, and tagging.
Install Python 3.10+ and set up a virtual environment using uv, then install dependencies from requirements.txt. Configure the MCP server in Claude for Desktop by adding an entry in claude_desktop_config.json pointing to the DeltaTask directory and running server.py with uv. After restarting Claude, access the DeltaTask tools via the hammer icon.
Python 3.10+ and SQLite3 are required. Obsidian is optional for markdown integration.
All data is stored locally in a SQLite database. No external servers are used.
It provides CRUD operations for tasks, search, sync with Obsidian, subtask management, tagging, and statistics retrieval.
Edit `claude_desktop_config.json` to add a `deltatask` entry with the command `uv` and arguments pointing to the DeltaTask directory and `server.py`.
Yes, the Obsidian integration is optional. The core task management and MCP server function independently.

ListingGood AI Recommendation Engine — a hosted MCP server + Claude/Cursor skills that make Amazon's AI recommend your products. Free no-login scan: https://listinggood.com/scan Get API key: https://listinggood.com/deve

Use My AskAI to find product, setup, integration, API, feature, pricing, and troubleshooting information. Search the public knowledge base, read complete documentation and OpenAPI files, and estimate pricing from monthly

Fdback.io is a user feedback platform (feedback board, roadmap, changelog) with a built-in remote MCP server - no local install, connect any MCP client with a URL and API key. Your AI agents can: - List, search, and rea
Human feedback for AI agents — remote MCP server at twocents.page/mcp (share_page / get_feedback)

Publish beautiful Markdown docs instantly from any AI agent. Zero-config remote MCP server — your LLM pastes Markdown, gets back a shareable page. Free, no signup needed.
Comments