How to Use the E2B MCP in LlamaIndex

Q: How does LlamaIndex track active E2B sandboxes?

The agent calls listsandboxes to retrieve metadata for all running microVMs. LlamaIndex can then use this data to determine if a specific runtime session is still available.

Q: What runtimes are available for code execution?

When calling createsandbox, you can choose base, python3, or node templates. This lets your agent run Python or JavaScript workloads in a tailored environment.

Run code in secure 150ms microVMs and index the raw outputs directly into your LlamaIndex vector store.

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 LlamaIndex

Create your Vinkius account to connect E2B to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index raw code execution outputs into LlamaIndex

LlamaIndex works best when it can turn dynamic data into searchable knowledge. By using this MCP Server, your agent can call `create_sandbox` to run Python scripts or terminal commands and capture the raw standard output. Instead of letting that output vanish, LlamaIndex indexes the execution logs and file contents directly into your vector database. This allows your RAG pipeline to query past runtime results during future user conversations.

Query active sandbox states using LlamaIndex RAG

When running multiple data analysis jobs, your agent needs to know what environments are currently active. This MCP Server lets LlamaIndex query `list_sandboxes` to get a list of active microVMs and index their metadata. This metadata helps your agent decide whether to spin up a new runtime with `create_sandbox` or reuse an existing one. It bridges the gap between static vector indexes and live, running cloud environments.

Clean up stale LlamaIndex sandboxes automatically

Leftover environments waste resources and cloud spend. Your LlamaIndex agent can monitor active runs and call `kill_sandbox` as soon as a data ingestion or code execution task completes. This tight lifecycle management keeps your vector index aligned with actual running infrastructure. It ensures that your agent only queries active, valid environments while cleaning up stale filesystem states.

Setup guide

Set up E2B MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all E2B MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to E2B tools.",
)
response = await agent.run("List recent E2B data")

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 LlamaIndex

You install the LlamaIndex MCP tool package and initialize the client. Then, you convert `create_sandbox` and `kill_sandbox` into LlamaIndex tool specs and pass them to your agent.

Yes. Your agent can run code to generate files in the sandbox, read those files, and then use LlamaIndex to parse and index their contents into your vector store.

The agent calls `list_sandboxes` to retrieve metadata for all running microVMs. LlamaIndex can then use this data to determine if a specific runtime session is still available.

When calling `create_sandbox`, you can choose base, python3, or node templates. This lets your agent run Python or JavaScript workloads in a tailored environment.

Every execution occurs inside a single-use Firecracker microVM. LlamaIndex only indexes the outputs you choose, and calling `kill_sandbox` completely destroys the VM filesystem, ensuring no data persists in the cloud.

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