How to Use the E2B MCP in AutoGen

Q: Can multiple AutoGen agents share a single E2B sandbox?

Yes. One agent can call createsandbox and share the resulting sandbox ID with other agents in the group, allowing them to run commands in the same environment.

Let your AutoGen agents debate, write, and execute code safely inside isolated 150ms Firecracker sandboxes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect E2B MCP to AutoGen

Create your Vinkius account to connect E2B to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup E2B with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent code verification inside AutoGen

AutoGen relies on multiple agents collaborating to solve problems. With this MCP Server, your coding agent can call `create_sandbox` to run a script, while your critic agent reviews the output to verify correctness. If the execution fails, the critic agent can suggest fixes, and the coder can run the revised script in the same microVM. This collaborative loop happens entirely within a secure, ephemeral environment.

Manage shared sandbox lifecycles across AutoGen conversations

In an AutoGen group chat, multiple agents need access to the same workspace. Using this MCP Server, one agent can initialize the environment using `create_sandbox`, and other agents can interact with the same filesystem. Agents can call `list_sandboxes` to coordinate who is using which microVM. Once the group conversation reaches a consensus, the coordinator agent calls `kill_sandbox` to clean up the workspace.

Prevent malicious code execution in AutoGen loops

Autonomous agent loops can sometimes write dangerous code or infinite loops. Running these scripts inside an isolated Firecracker microVM means your host system is completely safe from accidental damage. Since the default timeout is 300 seconds, runaway scripts are automatically stopped. Your AutoGen supervisor agent can also call `kill_sandbox` immediately if it detects malicious behavior.

Setup guide

Set up E2B MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes E2B tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="E2B_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent E2B data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="E2B_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent E2B data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by E2B. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect E2B now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about E2B MCP in AutoGen

You register the MCP tools with your AutoGen agent configuration. This exposes `create_sandbox` and `kill_sandbox` to your agents, allowing them to run code during their conversations.

Yes. One agent can call `create_sandbox` and share the resulting sandbox ID with other agents in the group, allowing them to run commands in the same environment.

The execution will automatically time out after 300 seconds, or another AutoGen monitoring agent can call `kill_sandbox` using the sandbox ID to terminate the VM instantly.

Yes. The sandbox is a full Linux environment, allowing your agents to run shell commands, install packages, and manage files within the microVM.

Absolutely. Every sandbox is a zero-trust, ephemeral microVM isolated at the hypervisor level. Once your conversation ends and `kill_sandbox` is called, all sandboxed files and execution states are completely erased.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript