Pica

🚀 Pica MCP Server

A TypeScript-typed Model Context Protocol (MCP) server built for Pica.

Installation Video: https://youtu.be/JJ62NUEkKAs

Demo Video: https://youtu.be/0jeasO20PyM

🚀 Quick Start

What is MCP?

Model Context Protocol (MCP) is a system that allows AI applications like Claude Desktop to connect to external tools and services. It provides a clear and secure way for AI assistants to interact with local services and APIs while keeping users in control.

What is Pica?

Pica is a powerful automation platform that helps you connect and automate various applications. With Pica, you can easily create complex business processes across different service platforms.

📦 Installation

Using npx

npx pica-mcp-server

Using Smithery CLI

smithery install @picahq/pica

Docker Installation

# Dockerfile
FROM node:16

WORKDIR /app

COPY package*.json ./

RUN npm install --production

CMD ["node", "index.js"]

Environment Configuration

Setting API Key

Create a .env file in your project directory:

PORT=3000
API_KEY=your_api_key_here

Docker Run Command

docker build -t pica-mcp .
docker run -p 3000:3000 --env-file .env pica-mcp

Manual Installation

1. Clone the repository:

   git clone https://github.com/picahq/pica.git
   cd pica
   

2. Install dependencies:

   npm install
   

3. Start the server:

   node index.js
   

💻 Usage Examples

Communication and Productivity

• Send an email to colleagues with a meeting summary using Gmail.
• Schedule a meeting for next Tuesday at 2 PM in Google Calendar.
• Send a message containing the latest campaign metrics to the #marketing channel in Slack.
• Find Google Drive documents related to the Q3 plan.

Data Access and Analysis

• List the top 10 largest customers in a PostgreSQL database.
• Create a new worksheet in Google Sheets and enter sales data.
• Query Salesforce for opportunities closing this month.
• Update the project status in a Notion database.

Business Operations

• Create a support ticket in Zendesk based on customer feedback.
• Process a customer refund in Stripe.
• Add a new lead from a website inquiry to HubSpot.
• Generate an invoice for a client project in QuickBooks.

AI and Content

• Generate an image using DALL-E based on product specifications.
• Transcribe a meeting recording using ElevenLabs.
• Research market trends using Tavily or SerpApi.
• Analyze customer sentiment in support tickets.

📄 License

This project is licensed under the GPL-3.0 license. Please refer to the LICENSE file for details.