A Model Context Protocol (MCP) server that integrates with Pica, enabling seamless interaction with various third-party services through a standardized interface. This server provides direct access to platform integrations, actions, execution capabilities, and robust code generation capabilities.
- list_pica_integrations - List all available platforms and your active connections
 - search_pica_platform_actions - Search for available actions for a specific platform
 - get_pica_action_knowledge - Get detailed documentation for a specific action including parameters and usage
 - execute_pica_action - Execute API actions with full parameter support
 
- Connect to 100+ platforms through Pica
 - Manage multiple connections per platform
 - Access real-time connection status
 
- Execute actions immediately (e.g. "read my last gmail email", "send a message to the slack channel #general")
 - Generate integration code (e.g. "build a form to send emails using gmail", "create a UI for messaging")
 - Intelligent context handling
 
- Never exposes secrets in generated code
 - Uses environment variables: 
PICA_SECRET,PICA_[PLATFORM]_CONNECTION_KEY - Sanitized request configurations for production use
 
- Execute actions directly through the MCP interface
 - Support for all HTTP methods (GET, POST, PUT, DELETE, etc.)
 - Handle form data, URL encoding, and JSON payloads
 - Pass path variables, query parameters, and custom headers
 
- All requests authenticated through Pica's secure proxy
 - No need to manage individual platform API keys
 - Environment variable configuration for security
 
npm install @picahq/mcpPICA_SECRET=your-pica-secret-keyGet your Pica secret key from the Pica dashboard.
npx @picahq/mcpTo use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "pica": {
      "command": "npx",
      "args": ["@picahq/mcp"],
      "env": {
        "PICA_SECRET": "your-pica-secret-key"
      }
    }
  }
}In the Cursor menu, select "MCP Settings" and update the MCP JSON file to include the following:
{
  "mcpServers": {
    "pica": {
      "command": "npx",
      "args": ["@picahq/mcp"],
      "env": {
        "PICA_SECRET": "your-pica-secret-key"
      }
    }
  }
}The remote MCP server is available at https://mcp.picaos.com.
Build the Docker Image:
docker build -t pica-mcp-server .Run the Docker Container:
docker run -e PICA_SECRET=your_pica_secret_key pica-mcp-serverYou can deploy this MCP server to Vercel for remote access:
- 
Install dependencies including Vercel adapter:
npm install @vercel/mcp-adapter zod
 - 
Deploy to Vercel:
vercel
 - 
Configure your MCP client to use the remote server:
- For Cursor: 
https://your-project.vercel.app/api/mcp - For Claude/Cline: Use 
npx mcp-remote https://your-project.vercel.app/api/mcp 
 - For Cursor: 
 
See DEPLOYMENT.md for detailed Vercel deployment instructions.
Build Email Form:
"Create me a React form component that can send emails using Gmail using Pica"
Linear Dashboard:
"Create a dashboard that displays Linear users and their assigned projects with filtering options using Pica"
QuickBooks Table:
"Build a paginatable table component that fetches and displays QuickBooks invoices with search and sort using Pica"
Slack Integration:
"Create a page with a form that can post messages to multiple Slack channels with message scheduling using Pica"
Gmail Example:
"Get my last 5 emails from Gmail using Pica"
Slack Example:
"Send a slack message to #general channel: 'Meeting in 10 minutes' using Pica"
Shopify Example:
"Get all products from my Shopify store using Pica"
List all available Pica integrations and platforms. Always call this tool first to discover available platforms and connections.
Parameters: None
Returns:
connections: Array of active user connections with platform and keyavailablePlatforms: Array of active platforms with name and categorysummary: Statistics including connected and available counts
Search for relevant actions on a specific platform using a query. Returns the top 5 most relevant actions based on vector similarity search.
Parameters:
platform(string, required): Platform name in kebab-case format (e.g., 'ship-station', 'shopify')query(string, required): Search query describing what you want to do (e.g., 'search contacts', 'create invoice', 'send email')agentType(enum, optional): Agent context type - either"execute"or"knowledge". Defaults to"knowledge"if not specified- Use 
"execute"when the user wants to perform an action - Use 
"knowledge"when the user wants to get information or write code 
- Use 
 
Returns:
actions: Array of up to 5 most relevant actions, each with:actionId: Unique identifier for the actiontitle: Human-readable action namemethod: HTTP method (GET, POST, etc.)path: API endpoint path
metadata: Search metadata with platform, query, and result count
Get comprehensive documentation for a specific action. Must be called before execute_pica_action to understand requirements.
Parameters:
actionId(string, required): Action ID from search_pica_platform_actionsplatform(string, required): Platform name in kebab-case format
Returns:
- Detailed action documentation
 - Parameter requirements and structure
 - API-specific guidance and caveats
 - Usage examples and implementation notes
 
Execute a Pica action to perform operations on third-party platforms. Critical: Only call this when the user wants to execute an action, not when building applications.
Parameters:
platform(string, required): Platform nameactionId(string, required): Action ID from search_pica_platform_actionsconnectionKey(string, required): Connection key for the platformdata(object, optional): Request body datapathVariables(object, optional): Variables to replace in the pathqueryParams(object, optional): Query parametersheaders(object, optional): Additional headersisFormData(boolean, optional): Send as multipart/form-dataisFormUrlEncoded(boolean, optional): Send as URL-encoded form data
Returns:
requestConfig: Sanitized request configurationresponseData: Actual API response from the platform
The server implements comprehensive error handling:
- β Parameter validation for all tools
 - β Connection verification before execution
 - β Path variable validation and substitution
 - β Graceful handling of API failures
 - β Detailed error messages for debugging
 - β MCP-compliant error responses
 
- π Single environment variable required: 
PICA_SECRET - π‘οΈ All requests authenticated through Pica's secure proxy
 - π No direct platform API key management needed
 - π« Secrets never exposed in responses
 - β Request configurations sanitized
 - π Sensitive data filtered from logs
 - π‘οΈ Input validation and sanitization
 
MIT
For support, please contact [email protected] or visit https://picaos.com