PocketBase Task MCP Server
MCP server integrating with PocketBase to manage tasks and projects. Enables AI models to create tasks, list tasks with status filters, and browse projects.
README
https://claude.ai/chat/4dea4e6a-4f62-44b0-8a96-f87167a17fef https://claude.ai/public/artifacts/8f2db72a-f062-4d0c-b64c-e7f4018910d6
cloudflared tunnel --url http://localhost:3001
- Email:
test@example.com - Password:
password123
PocketBase Task MCP Server
A Model Context Protocol (MCP) server that integrates with PocketBase to manage tasks and projects. This server allows AI models (like Claude) to create tasks, list tasks with status filters, and browse projects.
Now running over HTTP - Easy to test locally and ready for deployment!
Features
- HTTP Transport: Simple URL-based access, no complex configuration needed
- Tool Chaining: Automatically links tasks to projects by fetching IDs first
- Project Management: List all projects from the
projectscollection - Task Management: Create tasks in the
taskcollection with mandatory project relationships - Status Filtering: List tasks and filter by 'Pending' or 'Completed' status
- Environment Driven: Securely managed via
.envfile for PocketBase authentication - Easy Testing: Simple health check endpoint and MCP Inspector support
โก Quick Start
# 1. Install dependencies
npm install
# 2. Create .env file
echo "PB_AUTH_TOKEN=your_super_admin_token_here" > .env
# 3. Build the project
npm run build
# 4. Start the server
node dist/index.js
Your server is now running at http://localhost:3000!
Test it: Open http://localhost:3000/health in your browser.
๐ Getting Started
1. Prerequisites
- Node.js (v18+)
- PocketBase running locally at
http://127.0.0.1:8090 - A PocketBase Super Admin token.
2. Installation
npm install
3. Configuration
Create a .env file in the project root:
PB_AUTH_TOKEN=your_super_admin_token_here
๐ ๏ธ Development & Debugging
Build the Project
Compile the TypeScript code into JavaScript:
npm run build
Start the HTTP Server
Run the server locally:
node dist/index.js
The server will start on http://localhost:3000 (or the port specified in your .env file).
You should see output like:
MCP server running on http://localhost:3000
Health check: http://localhost:3000/health
MCP endpoint: http://localhost:3000/mcp
Test the Server
Visit the health check endpoint in your browser:
http://localhost:3000/health
You should see:
{"status":"ok","message":"PMS MCP Server is running"}
Optional Port Configuration
Add to your .env file to change the port:
PORT=3000
PB_AUTH_TOKEN=your_super_admin_token_here
๐ Available Tools
list_projects: Fetch all projects and their IDs.create_task: Create a new task (requirestask_title,eta,status, andproject_id).list_tasks: List all tasks with optional status filtering.
๐งช Testing the Tools
You can test the MCP server using the MCP Inspector or by connecting via the HTTP endpoint at http://localhost:3000/mcp.
Using MCP Inspector
npx @modelcontextprotocol/inspector
Then connect to: http://localhost:3000/mcp
๐ Why HTTP Over Stdio?
Advantages:
- No Configuration Files: No need to edit
claude_desktop_config.jsonor other complex configs - Easy Testing: Simple URL access via browser or tools like Postman
- Remote Ready: Can be deployed to a server and accessed from anywhere
- Multiple Clients: Multiple applications can connect simultaneously
- Better Debugging: Easy to monitor requests and responses with standard HTTP tools
Connecting from MCP Clients:
When using MCP-compatible clients, connect to:
http://localhost:3000/mcp
๐ Dependencies
@modelcontextprotocol/sdk: Core MCP functionalitypocketbase: PocketBase JS SDKexpress: HTTP server frameworkcors: Cross-Origin Resource Sharing middlewarezod: Schema validationdotenv: Environment variable management
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.