Activepieces MCP server

Activepieces is an open source automation platform that works as a Model Context Protocol (MCP) server. With over 280+ integrations ("pieces"), Activepieces allows you to build automated workflows between different services and applications, and can be used with LLMs through tools like Claude Desktop, Cursor, or Windsurf.

Installation

Docker Installation

The easiest way to install Activepieces is using Docker:

docker run -d \
  --name activepieces \
  -p 8080:80 \
  -e AP_DB_TYPE=sqlite \
  -e AP_ENCRYPTION_KEY=<random-secret> \
  -e AP_JWT_SECRET=<random-secret> \
  activepieces/activepieces:latest

Replace <random-secret> with your own secure values for both environment variables.

After installation, access the platform at http://localhost:8080.

Environment Variables

Here are some important environment variables you might need to configure:

AP_DB_TYPE: Database type (sqlite, postgres)
AP_ENCRYPTION_KEY: Secret key for encrypting sensitive data
AP_JWT_SECRET: Secret key for JWT token generation
AP_FRONTEND_URL: URL where the frontend is hosted (default: http://localhost:8080)

For PostgreSQL configuration, additional variables are needed:

AP_POSTGRES_DATABASE: Database name
AP_POSTGRES_HOST: Database host
AP_POSTGRES_PASSWORD: Database password
AP_POSTGRES_PORT: Database port (default: 5432)
AP_POSTGRES_USERNAME: Database username

Using Activepieces

Building Your First Flow

1. Access the platform at your installation URL (default: http://localhost:8080)
2. Sign up for a new account
3. Navigate to the dashboard and click "Create Flow"
4. Select a trigger (e.g., webhook, schedule, or one of the available integrations)
5. Add actions to your flow by clicking the "+" button
6. Configure each action with the necessary settings
7. Test your flow using the "Test Flow" button
8. Publish your flow when you're satisfied with the results

Working with Pieces

Pieces are integrations that connect with external services. To use a piece:

1. Add a new step to your flow
2. Select the piece you want to use from the catalog
3. Connect your account to the service if required
4. Configure the action parameters
5. Save your changes

Using AI Capabilities

Activepieces offers AI features that can be used in your flows:

1. AI pieces for services like OpenAI, Claude, etc.
2. Code piece with AI assistance
3. AI-powered agents

Using Loops and Branches

For more complex workflows:

1. Use the Loop step to iterate through data collections
2. Use the Branch step to create conditional logic in your flow
3. Configure conditions based on data from previous steps

Using Activepieces as an MCP Server

To use Activepieces with LLMs as an MCP server:

1. Ensure your Activepieces instance is accessible to your LLM tool
2. Connect your Claude Desktop, Cursor, or Windsurf to Activepieces
3. The available pieces will appear as tools that the LLM can use

Troubleshooting

Common Issues

• Connection Problems: Ensure your database credentials are correct
• Authentication Errors: Check your JWT and encryption key settings
• Integration Issues: Verify API keys and permissions for external services

Logs

To check logs in Docker installation:

docker logs activepieces

For more detailed logs, you can adjust the log level:

docker run -e AP_LOG_LEVEL=debug ... activepieces/activepieces:latest

Advanced Configuration

Custom Templates

You can create custom templates for common workflows:

1. Build a flow with the steps you want to template
2. Click "Save as Template"
3. Your template will be available when creating new flows

Multiple Languages

Activepieces supports multiple languages in the interface. You can change the language from the user settings panel.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "activepieces" '{"command":"npx","args":["-y","@activepieces/cli"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "activepieces": {
            "command": "npx",
            "args": [
                "-y",
                "@activepieces/cli"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "activepieces": {
            "command": "npx",
            "args": [
                "-y",
                "@activepieces/cli"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect