Follow Plan MCP Server
An MCP server for intelligent project planning and task management featuring task tracking, bug reporting, and feature specification with SQLite persistence. It includes full-text search capabilities and automatic filesystem synchronization to keep project data organized and accessible.
README
Follow Plan MCP Server
A comprehensive Model Context Protocol (MCP) server for intelligent project planning and task management with SQLite persistence and full-text search capabilities.
Features
- Task Management: Create, update, and track tasks with status, priority, and progress
- Feature Planning: Manage user stories, epics, and feature specifications
- Bug Tracking: Report and track bugs with severity levels and reproduction steps
- Rule Engine: Define project rules, validations, and automation guidelines
- Full-Text Search: Advanced search across all plan items with relevance scoring
- SQLite Storage: Persistent storage with FTS5 full-text search indexing
- Auto-Sync: Automatic synchronization between database and filesystem
- Backup/Restore: Database backup and restore functionality
Quick Start
1. Install Dependencies
npm install
2. Build the Project
npm run build
3. Start the MCP Server
npm start /path/to/your/project
The server will create a .plan directory in your project with the following structure:
.plan/
├── database.db # SQLite database
├── index.md # Project overview
├── tasks/ # Task files
├── features/ # Feature files
├── bugs/ # Bug files
├── rules/ # Rule files
├── workflows/ # Workflow documentation
├── changelog/ # Project changelog
└── tmp/ # Temporary files and logs
MCP Tools
Task Management
create_task- Create a new taskupdate_task- Update an existing taskget_task- Get task details by IDlist_tasks- List tasks with optional filtersdelete_task- Delete a task
Feature Management
create_feature- Create a new featureupdate_feature- Update an existing featureget_feature- Get feature details by IDlist_features- List features with optional filtersdelete_feature- Delete a feature
Bug Tracking
create_bug- Create a new bug reportupdate_bug- Update an existing bugget_bug- Get bug details by IDlist_bugs- List bugs with optional filtersdelete_bug- Delete a bug
Rule Management
create_rule- Create a new project ruleupdate_rule- Update an existing ruleget_rule- Get rule details by IDlist_rules- List rules with optional filtersdelete_rule- Delete a rule
Search & Discovery
search- Search across all plan itemsadvanced_search- Advanced search with filters
Data Management
backup_database- Create a database backuprestore_database- Restore from backupsync_filesystem- Sync database to filesystem
MCP Resources
plan://index- Project plan overview (Markdown)plan://tasks- All tasks (JSON)plan://features- All features (JSON)plan://bugs- All bugs (JSON)plan://rules- All rules (JSON)plan://stats- Project statistics (JSON)
Configuration
Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"follow-plan": {
"command": "node",
"args": [
"/path/to/follow-plan-mcp/dist/index.js",
"/path/to/your/project"
],
"env": {}
}
}
}
Environment Variables
LOG_LEVEL- Set logging level (debug, info, warn, error)PLAN_AUTO_SYNC- Enable/disable auto-sync (default: true)PLAN_BACKUP_INTERVAL- Backup interval in seconds (default: 1800)
Development
Build
npm run build
Test
npm test
npm run test:coverage
Lint
npm run lint
npm run lint:fix
Format
npm run format
Database Schema
The server uses SQLite with FTS5 full-text search. Key tables:
tasks- Project tasksfeatures- Feature specificationsbugs- Bug reportsrules- Project rulesmessages- Communication logsprompts- AI prompt templatescascades- Automation workflowsfts_search- Full-text search index
Architecture
src/
├── index.ts # Main MCP server
├── types/ # TypeScript type definitions
├── services/ # Business logic services
│ ├── database-service.ts
│ ├── task-service.ts
│ ├── feature-service.ts
│ ├── bug-service.ts
│ ├── rule-service.ts
│ ├── search-service.ts
│ └── persistence-service.ts
├── handlers/ # MCP request handlers
│ ├── tools.ts
│ ├── resources.ts
│ ├── validation.ts
│ └── search-handlers.ts
├── utils/ # Utility functions
└── constants/ # Application constants
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Run the test suite
- Submit a pull request
License
MIT License - see LICENSE file for details
Support
For issues and questions:
- GitHub Issues: [Report a bug or request a feature]
- Documentation: See the
/docsdirectory - Examples: See the
/examplesdirectory
Follow Plan MCP - Intelligent project planning for the AI age 🚀
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.