bytechef MCP工具

Build Workflows with Ease using Copilot

Build AI agents and workflows by talking to ByteChef. The Copilot generates workflows from a sentence, drops in configured agent steps, explains failed runs and suggests fixes.

---

Docker Compose (Fastest Setup)

Requirement: Docker Desktop

This is the fastest way to start ByteChef. Download the docker-compose.yml file from the repository:

curl -O https://raw.githubusercontent.com/bytechefhq/bytechef/master/docker-compose.yml
docker compose -f docker-compose.yml up

Both PostgreSQL database and ByteChef containers will start automatically.

Open <http://localhost:8080/login> → Create Account → sign in.

Docker (Manual Setup)

If Docker Compose isn't supported in your environment, follow these steps:

#### 1. Create Docker Network

docker network create -d bridge bytechef_network

#### 2. 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

#### 3. 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=e48612ba1fd46fa7089fe9f5085d8d164b53ffb2 \
    --network bytechef_network \
    docker.bytechef.io/bytechef/bytechef:latest

Note: Use -d flag instead of -it to run in detached mode.

Open <http://localhost:8080/login> → Create Account → sign in.

Build your first agent in 60 seconds

1. New Project → New Workflow,
2. Add a trigger
3. Add the AI Agent component
4. Pick a model, attach tools from 200+ connectors, optionally add a knowledge base and guardrails
5. Fill the necessary credentials
6. Configure each component's parameters in the properties panel
7. Test your workflow
8. Deploy

---

Quick Start

**The open-source platform that unifies AI agent orchestration and workflow automation**

Workflow Automation

• Visual editor with JSON underneath, Git-friendly
• Flow controls — condition · switch · loop · each · parallel · branch · sub-workflows
• Triggers — webhook · schedule · polling · app-event · manual · form
• Polyglot code — Java · JavaScript · Python · Ruby on GraalVM
• Durable execution on the Atlas runtime, Postgres-backed, queue-mode for horizontal scale (memory · Redis · RabbitMQ · Kafka · JMS · AMQP · SQS)
• Workflows-as-APIs — workflows can be an authenticated HTTP endpoint
• Git-native — push from the UI, environments backed by branches

---