agent-sandbox MCP工具

1, Installation

You can install Agent-Sandbox by applying the provided install.yaml file to your Kubernetes cluster.

requires Kubernetes version 1.26 or higher.

kubectl create namespace agent-sandbox
kubectl apply -nagent-sandbox -f install.yaml

apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: agent-sandbox
  namespace: agent-sandbox
spec:
  ingressClassName: ingress-nginx
  rules:
  - host: agent-sandbox.your-host.com
    http:
      paths:
      - backend:
          service:
            name: agent-sandbox
            port:
              number: 80
        path: /

Quick Start

2, Usage

The Agent-Sandbox provides a RESTful API or MCP to manage sandboxes. The typical workflow involves creating a sandbox, accessing it, and then deleting it when no longer needed.

2.2, Use RESTful API

You can also manage sandboxes manually using the RESTful API provided by Agent-Sandbox.

#### I, Create a Sandbox You can create a new sandbox by sending a POST request to the /api/v1/sandbox endpoint with the desired configuration. For example, to create an aio sandbox and name it sandbox-01, you can use the following curl command or programmatically call the API:

curl --location '/api/v1/sandbox' \
--header 'Content-Type: application/json' \
--data '{"name":"sandbox-01"}'

curl --location '/api/v1/sandbox' \
--header 'Content-Type: application/json' \
--data '{"name":"sandbox-01","image":"enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest"}'

import requests
import json

url = "/api/v1/sandbox"

payload = json.dumps({
  "name": "sandbox-01"
})
headers = {
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

{
    "code": "0",
    "data": "Sandbox sandbox-01 created successfully"
}