Pica MCP Server for Claude Desktop Integration

Overview

The Pica MCP Server is a Model Context Protocol (MCP) server built in TypeScript, designed to integrate with Claude Desktop and other AI applications. It enables secure and seamless interactions with over 70 third-party services and APIs through natural language requests. This server empowers users to automate workflows, access multiple data sources, and enhance the capabilities of AI assistants like Claude.

Key Features

• Access Multiple Data Sources: Query databases, fetch files, and retrieve information across connected services.
• Automate Workflows: Trigger actions and automate tasks across platforms like Gmail, Slack, Salesforce, and more.
• Enhance LLM Capabilities: Extend Claude Desktop's functionality with real-world API access.

What is MCP?

Model Context Protocol (MCP) is a system that allows AI applications, such as Claude Desktop, to connect securely to external tools and data sources. It provides a standardized way for AI assistants to interact with local services and APIs while maintaining user control.

What is Pica?

Pica is a powerful agentic tooling platform that enables connections to over 70 third-party services and applications. The Pica MCP Server bridges Claude Desktop and these services, allowing users to perform complex tasks through natural language commands.

Supported Connections

Pica supports a wide range of services across categories like:
- Communication & Collaboration: Gmail, Slack, Notion, Google Drive.
- Data & Analytics: PostgreSQL, BigQuery, Google Sheets.
- Business & CRM: Salesforce, HubSpot, Zendesk.
- AI & ML Services: OpenAI, Anthropic, Gemini.
- E-commerce & Financial: Shopify, Stripe, QuickBooks.

Installation 🛠️

Using npx

Run the server directly with npx:

npx @picahq/pica-mcp

Or install it globally:

npm install -g @picahq/pica-mcp

Installing via Smithery

Automatically install Pica for Claude Desktop using Smithery:

npx -y @smithery/cli install @picahq/pica --client claude

Environment Setup

Set the required Pica API key:

export PICA_SECRET=your_pica_secret_key

Using Docker

Build the Docker image:

docker build -t pica-mcp-server .

Run the container:

docker run -e PICA_SECRET=your_pica_secret_key pica-mcp-server

Manual Installation

Install dependencies and build the server:

npm install
npm run build

For development with auto-rebuild:

npm run watch

Using Claude Desktop

Add the server configuration to your claude_desktop_config.json file.

Docker Configuration

{
  "mcpServers": {
    "pica-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "PICA_SECRET=YOUR_PICA_SECRET_KEY",
        "pica-mcp-server"
      ]
    }
  }
}

Manual Configuration

{
  "mcpServers": {
    "pica-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/pica-mcp-server/build/index.js"
      ],
      "env": {
        "PICA_SECRET": "YOUR_PICA_SECRET_KEY"
      }
    }
  }
}

Debugging

Use the MCP Inspector for debugging:

npm run inspector

Example Usage ✨

Communication & Productivity

• Send emails via Gmail.
• Create calendar events in Google Calendar.
• Send Slack messages to specific channels.
• Search for documents in Google Drive.

Data Access & Analysis

• Query PostgreSQL databases.
• Create Google Sheets with sales data.
• Retrieve Salesforce opportunities.
• Update Notion databases.

Business Operations

• Create Zendesk support tickets.
• Process Stripe refunds.
• Add leads to HubSpot.
• Generate QuickBooks invoices.

AI & Content

• Generate images with DALL-E.
• Transcribe meeting recordings with ElevenLabs.
• Research market trends using Tavily or SerpApi.
• Analyze customer sentiment from support tickets.

License

This project is licensed under the GPL-3.0 license. See the LICENSE file for details.

About

The Pica MCP Server is a TypeScript-based implementation of the Model Context Protocol, designed to integrate Claude Desktop with Pica's extensive tooling platform.

For more details, visit docs.picaos.com/sdk/anthropic-mcp.