1. Conduid
  2. Productivity
  3. Lazy Llms
MCP server · Productivity

Lazy Llms

An LLM-native project management system — a self-hosted, lightweight Jira alternative where AI agents are first-class citizens via 23 MCP tools, with a web UI and git integration.

Unclaimed last commit a year ago productivity
48Fair

Scored 5 months ago · breakdown

About Lazy Llms

Lazy Llms is an MCP server published by Juliusolsson05 in the Productivity category: an LLM-native project management system — a self-hosted, lightweight Jira alternative where AI agents are first-class citizens via 23 MCP tools, with a web UI and git integration.

The repository has 15 stars and 1 forks, with the last commit a year ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/Juliusolsson05/lazy-llms

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Lazy Llms

Powered by Claude · Grounded in docs

I know everything about Lazy Llms. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository yesterday. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • !License declaredNo license file. Legally you have no right to use it in a product.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • !Dependencies pinnedNo lockfile. Installs can pull different code over time.
  • !No dynamic code executionSource scan found eval or shell execution. Review how tool inputs reach it before granting credentials.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

LLM-Native Project Management System

A project management system designed for LLM agents as first-class citizens. Track issues, log work, and manage projects with rich context - all optimized for AI workflows.

🚀 Quick Start (2 minutes)

One-Command Setup

make quickstart

This will:

  1. Install all dependencies
  2. Initialize the database
  3. Start the web UI at http://localhost:1929
  4. Copy Claude Desktop integration command to clipboard

Manual Setup

# 1. Install dependencies
pip install -r requirements.txt
cd mcp && pip install -r requirements.txt && cd ..

# 2. Initialize database
make init-db

# 3. Start services
make start  # Starts all services

🎯 Core Features

  • Rich Issue Tracking - Issues with comprehensive specs and technical approaches
  • Work Logging - Track development activity with artifacts and context
  • Git Integration - Automatic branch creation and commit formatting
  • Web UI - Visual dashboards and issue management at http://localhost:1929
  • MCP Tools - 23 tools for LLM agents to manage projects

📋 Basic Usage

Create an Issue

pm_create_issue --type feature --title "Add user auth" --description "..."

Start Work

pm_start_work --issue-key LAZY-001

Log Progress

pm_log_work --issue-key LAZY-001 --activity code --summary "Implemented JWT"

View Status

pm_status  # Project overview
pm_list_issues  # All issues

🔧 Claude Desktop Integration

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "pm-server": {
      "command": "python",
      "args": ["/path/to/lazy-llms/mcp/src/server.py"],
      "env": {
        "PM_DATABASE_PATH": "/path/to/lazy-llms/data/jira_lite.db"
      }
    }
  }
}

📂 Project Structure

lazy-llms/
├── mcp/src/              # MCP server for LLM integration
├── src/jira_lite/        # Web UI and database
├── data/                 # Database files
├── scripts/              # Utility scripts
└── docs/                 # Documentation

🛠 Available Commands

  • make quickstart - Complete one-command setup
  • make start - Start all services
  • make stop - Stop all services
  • make init-db - Initialize database
  • make clean - Clean generated files
  • make help - Show all commands

📚 Documentation

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

📄 License

MIT License


Built for AI agents, by AI agents 🤖

README fetched from the repository yesterday. The original is authoritative.

Questions

About Lazy Llms

How do I install Lazy Llms?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Lazy Llms safe to use with an AI agent?

Its trust score is 48 out of 100 (fair). It passes 1 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Lazy Llms still maintained?

The last commit was a year ago and 3 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.