TODO Assistant MCP Server
A simple MCP server for managing TODO tasks. Works with any MCP-compatible client.
Setup
- Install Python 3.10+
- Install dependencies:
pip install -r requirements.txtConnect to your MCP client
This server uses stdio transport — your MCP client starts and manages the server process automatically.
Add something like this to your client's MCP config (exact location depends on the client):
{
"mcpServers": {
"todo-assistant": {
"command": "python3",
"args": ["/full/path/to/server.py"]
}
}
}Replace /full/path/to/server.py with the actual absolute path.
Where to put this config:
| Client | Config location | |---|---| | Claude Desktop | ~/.config/Claude/claude_desktop_config.json (Linux) / ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) | | Cline (VS Code) | MCP Servers section in Cline settings, or ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json | | Other clients | Check your client's docs for MCP server configuration |
After adding the config, restart your client so it picks up the new server.
Tools
Once connected, your AI assistant can use these tools:
| Tool | What it does | |---|---| | add_task | Create a task (title, description, priority) | | list_tasks | List all/pending/completed tasks | | complete_task | Mark a task as done | | uncomplete_task | Mark a task as pending | | update_task | Edit a task's title, description, or priority | | delete_task | Remove a task |
Just ask your assistant in natural language, e.g. "add a task to buy groceries with high priority" or "show my pending tasks".
Storage
Tasks are saved to tasks.json in the server directory.
