planning-task-mcp
Full autonomous project management MCP server enabling AI assistants to manage projects, sprints, tasks, bugs, proposals, and team collaboration via natural language.
README
planning-task-mcp
MCP Server for full autonomous project management. Manage projects, sprints, tasks, bugs, proposals, and more — all from your AI coding assistant.
Works with Claude Code, Claude Desktop, Codex (OpenAI), Gemini CLI, Cursor, Windsurf, and VS Code Copilot.
Features
- Projects, sprints, and task management with User Stories
- Bug tracking and proposals
- Team collaboration (members, invitations, comments, notifications)
- Sprint planning from natural language documents
- Analytics dashboards and burndown charts
- Achievements and gamification
- Workflow automation rules
- Time tracking and retrospectives
Prerequisites
- Node.js >= 18
- A Firebase project with Realtime Database enabled
- A Firebase Service Account Key (JSON file)
Install
npm install -g planning-task-mcp
Setup
After installing, run the interactive setup:
planning-task-mcp-setup
This will:
- Ask for your Firebase Service Account Key path
- Configure your Firebase Database URL
- Set your default user ID and name
- Auto-register the MCP in all detected AI clients (Claude Code, Codex, Gemini, Cursor, etc.)
- Configure auto-approve permissions where supported
CLI mode (non-interactive)
planning-task-mcp-setup \
--sa-key /path/to/serviceAccountKey.json \
--db-url https://your-project-default-rtdb.firebaseio.com \
--user-id your-firebase-uid \
--user-name "Your Name"
Manual configuration
If you prefer to configure manually, add this to your MCP client config:
Claude Code (~/.mcp.json):
{
"mcpServers": {
"planning-task-mcp": {
"command": "planning-task-mcp",
"args": [],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/serviceAccountKey.json",
"FIREBASE_DATABASE_URL": "https://your-project-default-rtdb.firebaseio.com",
"DEFAULT_USER_ID": "your-uid",
"DEFAULT_USER_NAME": "Your Name"
}
}
}
}
Codex (~/.codex/config.toml):
[mcp_servers.planning-task-mcp]
command = "planning-task-mcp"
args = []
[mcp_servers.planning-task-mcp.env]
GOOGLE_APPLICATION_CREDENTIALS = "/path/to/serviceAccountKey.json"
FIREBASE_DATABASE_URL = "https://your-project-default-rtdb.firebaseio.com"
DEFAULT_USER_ID = "your-uid"
DEFAULT_USER_NAME = "Your Name"
Gemini CLI (~/.gemini/settings.json):
{
"mcpServers": {
"planning-task-mcp": {
"command": "planning-task-mcp",
"args": [],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/serviceAccountKey.json",
"FIREBASE_DATABASE_URL": "https://your-project-default-rtdb.firebaseio.com",
"DEFAULT_USER_ID": "your-uid",
"DEFAULT_USER_NAME": "Your Name"
}
}
}
}
Environment Variables
| Variable | Required | Description |
|---|---|---|
GOOGLE_APPLICATION_CREDENTIALS |
Yes | Path to Firebase Service Account Key JSON |
FIREBASE_DATABASE_URL |
Yes | Firebase Realtime Database URL |
DEFAULT_USER_ID |
No | Default Firebase Auth UID for operations |
DEFAULT_USER_NAME |
No | Default user display name |
Available Tools (70+)
| Category | Tools |
|---|---|
| Projects | create, list, get, update, delete, dashboard, summary |
| Sprints | create, list, get, update, delete, burndown, retrospective |
| Tasks | create, list, get, update, delete, search, assign, change status |
| Bugs | create, list, get, update, delete |
| Epics | create, list, get, update, delete, add/remove tasks |
| Proposals | create, list, get, update, delete, approve/reject |
| Comments | create, list, delete |
| Notifications | list, send, mark read, clear |
| Members | add, list, remove, change role |
| Invitations | send, list, accept, reject |
| Users | list, get, search |
| Analytics | project dashboard, developer workload, leaderboard |
| Planning | create full plan from document, create sprint plan |
| Templates | create, list, delete task templates |
| Workflows | create, list, update, delete, toggle automation rules |
| Time Tracking | create, list, delete time entries |
| Saved Views | create, list, delete custom views |
| Achievements | list, evaluate user achievements |
| Standup | get daily standup data |
Usage
Once configured, just talk to your AI assistant:
- "Create a new project called MyApp"
- "Plan a sprint from this requirements document"
- "Show me the burndown chart for the current sprint"
- "Assign task T-123 to user X"
- "What's the developer workload for this sprint?"
License
MIT
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.