bytechef
Open-source, AI-native, low-code platform for API orchestration, workflow automation, and AI agent integration across internal systems and SaaS products.
claude mcp add --transport stdio bytechefhq-bytechef docker run -i bytechef/bytechef:latest \ --env BYTECHEF_DATASOURCE_URL="jdbc:postgresql://postgres:5432/bytechef" \ --env BYTECHEF_DATASOURCE_PASSWORD="postgres" \ --env BYTECHEF_DATASOURCE_USERNAME="postgres" \ --env BYTECHEF_SECURITY_REMEMBER_ME_KEY="your-remember-me-key"
How to use
ByteChef is an open-source, self-hosted automation and API integration platform that lets you build, run, and manage low-code workflows across services and databases. This MCP server runs ByteChef in a containerized setup, exposing the web UI on port 8080 by default. You can start it via Docker (Compose is the fastest path) and then access the UI to create projects, workflows, triggers, and components. ByteChef provides a visual workflow editor, event-driven and scheduled workflows, a built-in code editor for multiple languages, over 200 built-in connectors, and the ability to extend with custom connectors. After starting, visit http://localhost:8080/login to create an account and begin building automation workflows. You can deploy workflows as APIs and manage authentication through the platform.
How to install
Prerequisites:
- Docker Desktop installed on your machine
- Basic familiarity with Docker and Docker Compose
Option A: Docker Compose (Fastest)
- Download the docker-compose.yml from the ByteChef repository
curl -O https://raw.githubusercontent.com/bytechefhq/bytechef/master/docker-compose.yml
- Start ByteChef with Docker Compose
docker compose -f docker-compose.yml up
This will spin up both PostgreSQL and ByteChef containers and wire them together.
Option B: Manual Docker Run
- Create a dedicated Docker network (recommended)
docker network create -d bridge bytechef_network
- Start PostgreSQL container
docker run --name postgres -d -p 5432:5432 \
--env POSTGRES_USER=postgres \
--env POSTGRES_PASSWORD=postgres \
--hostname postgres \
--network bytechef_network \
-v /opt/postgre/data:/var/lib/postgresql/data \
postgres:15-alpine
- Start ByteChef container
docker run --name bytechef -it -p 8080:8080 \
--env BYTECHEF_DATASOURCE_URL=jdbc:postgresql://postgres:5432/bytechef \
--env BYTECHEF_DATASOURCE_USERNAME=postgres \
--env BYTECHEF_DATASOURCE_PASSWORD=postgres \
--env BYTECHEF_SECURITY_REMEMBER_ME_KEY=your-remember-me-key \
--network bytechef_network \
docker.bytechef.io/bytechef/bytechef:latest
Note: Use -d to run detached if you don’t want to attach to the console.
Prerequisites recap: ensure Docker Desktop is installed, you have network access to pull the ByteChef image, and you configure environment variables for database access and security as needed.
Additional notes
Tips and caveats:
- The ByteChef UI will be available on port 8080 (http://localhost:8080/login) once containers are running.
- Update the BYTECHEF_SECURITY_REMEMBER_ME_KEY with a strong value for production usage.
- If you’re not using Docker Compose, ensure the PostgreSQL container (hosted at the specified URL) is accessible from the ByteChef container.
- You can customize database credentials and data volumes to persist data across restarts.
- For large deployments, consider configuring additional environment variables for connectors, authentication, and API access as documented in ByteChef docs.
- If you encounter port conflicts, adjust the -p 8080:8080 mapping in the docker run command or the docker-compose.yml ports.
Related MCP Servers
klavis
Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale
aci
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
claude-code-plugins-plus-skills
270+ Claude Code plugins with 739 agent skills. Production orchestration patterns, interactive tutorials (11 Jupyter notebooks), and CCPI package manager. 4.13.0
automagik-genie
🧞 Automagik Genie – bootstrap, update, and roll back AI agent workspaces with a single CLI + MCP toolkit.
rulego
A lightweight dependency-free workflow automation platform. Supports iPaaS, stream computing, MCP, and AI capabilities.
Playwright-AI-Agent-POM
Playwright AI Agent POM MCP ServerPlaywright AI Agent using Page Object Model (POM) architecture with MCP Server integration for automated web and mobile testing