How to Use the E2B MCP in Pydantic AI

Q: Can I run Python code directly in E2B using Pydantic AI?

Yes, your agent calls createsandbox with the python3 template to get an isolated Python environment. The agent then writes and executes scripts inside that microVM, returning the terminal outputs safely.

Execute untrusted code with type-safe validation using Pydantic AI and secure E2B 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 Pydantic AI

Create your Vinkius account to connect E2B to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Initialize E2B sandboxes with Pydantic AI

The `create_sandbox` tool provisions a secure, ephemeral Firecracker microVM in roughly 150 milliseconds. Your Pydantic AI agent uses this tool to spin up Python or JavaScript runtimes while validating the input parameters against strict schemas. This ensures your agent never passes malformed configuration to the sandbox. You get guaranteed runtime environments without worrying about silent configuration errors during initialization.

Safe teardown of active environments

The `kill_sandbox` tool deletes an active microVM and its entire filesystem permanently. Your Pydantic AI agent calls this tool to clean up resources, validating the target sandbox ID before sending the termination request. This validation prevents the agent from attempting to destroy non-existent or incorrect environments. It keeps your resource cleanup predictable and free of unhandled runtime exceptions.

Audit active microVMs programmatically

The `list_sandboxes` tool returns a structured list of all active microVMs in your E2B account. Your agent system parses this list into type-safe models using this MCP Server tool, letting you monitor resource usage with absolute structural certainty. This strict parsing eliminates unexpected API responses from breaking your monitoring loops. You can safely track concurrent sandboxes and build reliable auto-scaling logic.

Setup guide

Set up E2B MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "e2b-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to E2B tools.",
)

result = await agent.run("List recent E2B transactions")
print(result.output)

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 Pydantic AI

Use the unified MCPToolset class initialized with your Vinkius HTTP URL. Pass this toolset instance inside the toolsets list when defining your Pydantic AI Agent.

The framework validates every tool response against Pydantic models at runtime. If the sandbox metadata deviates from the expected schema, Pydantic AI raises a validation error immediately to prevent silent data corruption.

Yes, your agent calls create_sandbox with the python3 template to get an isolated Python environment. The agent then writes and executes scripts inside that microVM, returning the terminal outputs safely.

No, the MCP server runs externally on Vinkius. Your Pydantic AI agent connects over secure HTTP, meaning you do not need to manage local Firecracker installations or Docker daemons.

Every execution occurs in a dedicated, hardware-isolated Firecracker microVM that is completely segregated from other tenants. The code, input files, and output logs exist only within that ephemeral VM and are wiped permanently upon termination.

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