Activepieces is an open source automation platform that makes all of its pieces (integrations) available as MCP servers for use with LLMs through Claude Desktop, Cursor, or Windsurf. With over 280 integrations, it allows you to easily connect AI tools with various services and applications.
The quickest way to get started is by using Docker:
docker run -d \
--name activepieces \
-e AP_DB_TYPE=postgres \
-e AP_DB_URL=postgres://postgres:postgres@postgres:5432/postgres \
-e AP_ENCRYPTION_KEY=CHANGETHIS \
-e AP_FRONTEND_URL=http://localhost:8080 \
-p 8080:80 \
activepieces/activepieces:latest
Configure your installation with these important environment variables:
AP_DB_TYPE: Database type (postgres or mysql)
AP_DB_URL: Database connection string
AP_ENCRYPTION_KEY: Secret key for data encryption
AP_FRONTEND_URL: The URL where users will access the platform
For a more complete setup including a database, use this docker-compose.yml:
version: "3.8"
services:
postgres:
image: postgres:14.4
environment:
- POSTGRES_USER=postgres
- POSTGRES_PASSWORD=postgres
- POSTGRES_DB=postgres
ports:
- "5432:5432"
volumes:
- postgres_data:/var/lib/postgresql/data
activepieces:
image: activepieces/activepieces:latest
depends_on:
- postgres
ports:
- "8080:80"
environment:
- AP_DB_TYPE=postgres
- AP_DB_URL=postgres://postgres:postgres@postgres:5432/postgres
- AP_ENCRYPTION_KEY=CHANGETHIS
- AP_FRONTEND_URL=http://localhost:8080
volumes:
postgres_data:
Run it with:
docker-compose up -d
http://localhost:8080
(or your configured URL)Activepieces includes over 280 integrations (called "pieces") that enable connections to various services:
To use Activepieces pieces as MCP servers with LLMs:
# Install the Activepieces CLI
npm install -g @activepieces/cli
# Create an MCP server for a specific piece
ap mcp serve @activepieces/piece-gmail
This will start an MCP server that allows LLMs to interface with Gmail through tools like Claude Desktop or Cursor.
Create logic in your flows:
For custom logic:
// Example code step
export const code = async (inputs) => {
// Process data from previous steps
const processedData = inputs.data.map(item => {
return {
id: item.id,
normalized: item.value.toLowerCase()
};
});
return {
processedData
};
};
For production environments:
docker run -d \
--name activepieces \
-e AP_DB_TYPE=postgres \
-e AP_DB_URL=postgres://user:password@host:port/db \
-e AP_ENCRYPTION_KEY=LONG_RANDOM_STRING \
-e AP_FRONTEND_URL=https://your-domain.com \
-e AP_JWT_SECRET=ANOTHER_RANDOM_STRING \
-p 443:80 \
activepieces/activepieces:latest
For high-volume environments:
docker run -d \
--name activepieces \
-e AP_DB_TYPE=postgres \
-e AP_DB_URL=postgres://user:password@host:port/db \
-e AP_ENCRYPTION_KEY=LONG_RANDOM_STRING \
-e AP_FRONTEND_URL=https://your-domain.com \
-e AP_REDIS_URL=redis://redis:6379 \
-p 443:80 \
activepieces/activepieces:latest
If you encounter problems:
docker logs activepieces
If schema changes are needed after updates:
docker exec activepieces ap database migrate
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.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
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.
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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.