Pulse

Pulse

Pulse is a terminal-based task manager that integrates with AI agents via MCP, allowing agents to create, read, and manage tasks from the command line.

Category
Visit Server

README

Pulse - Terminal Task Manager

Stop context switching. Manage your projects where you code.

Pulse is a simple terminal-based task manager designed for developers who live in the command line. It combines a CLI, a TUI, and an MCP server to integrate seamlessly with AI agents.

Pulse TUI

The Vibe

I built Pulse for myself. Honestly, I wasn't happy with the existing tools. They were either too complex, mess up my projects, or just didn't feel right. I wanted something simple that let me group tasks with tags, move them through states, and most importantly, pause my work and pick it up days later without missing context.

This tool is 90% vibecoded. It's designed to feel good to use.

[!WARNING] Use at your own risk. While I use this daily, it is a personal project built for vibes first, stability second. Expect bugs, breaking changes, and occasional chaos.

Why Pulse?

  • 🧠 Stay in Flow: Keep a record of your tasks across sessions. Start a big feature today, pause, and pick it up days later without missing context.
  • 🛠️ Flexible: Control it your way—use the simple CLI, the interactive TUI, or let your AI agent handle it via MCP.
  • Version Controlled: Tasks are stored in simple YAML files. Commit them with your code or keep them separate—it's up to you.

Quick Start

1. Install & Usage

For Humans (CLI & TUI): Install globally to use the terminal interface.

bun install -g pulse-tm
pulse ui   # Launch the dashboard
pulse help # See all commands

For Agents (MCP): No global install needed. Just configure your agent (Claude/Cursor) to run:

bunx pulse-tm mcp

2. The "Agentic" Workflow

Pulse shines when paired with AI agents (like Cursor or Claude). Here is the suggested workflow:

Scenario 1: Planning

Ask your agent to read a PRD and plan the work.

Prompt: "Read PRD.md. Use Pulse to create a plan and generate tasks for this feature. Tag them with 'feature-x'."

What happens: The agent uses the MCP server to create a structured list of tasks in Pulse, organized by the tag you specified.

Scenario 2: Execution

Ask your agent to start working.

Prompt: "Work on the next task in 'feature-x'."

What happens: The agent reads the next pending task, writes the code to solve it, and marks the task as done in Pulse.

Documentation

Demo

Pulse Demo Video Placeholder

License

MIT License - see LICENSE file for details.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured