# How to integrate E2b MCP with LlamaIndex

```json
{
  "title": "How to integrate E2b MCP with LlamaIndex",
  "toolkit": "E2b",
  "toolkit_slug": "e2b",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/e2b/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/e2b/framework/llama-index.md",
  "updated_at": "2026-03-29T06:31:50.255Z"
}
```

## Introduction

This guide walks you through connecting E2b to LlamaIndex using the Composio tool router. By the end, you'll have a working E2b agent that can run a python script to analyze csv data, execute javascript code to validate user input, start a sandbox and list installed packages through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a E2b account through Composio's E2b MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate E2b with

- [ChatGPT](https://composio.dev/toolkits/e2b/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/e2b/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/e2b/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/e2b/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/e2b/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/e2b/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/e2b/framework/codex)
- [Cursor](https://composio.dev/toolkits/e2b/framework/cursor)
- [VS Code](https://composio.dev/toolkits/e2b/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/e2b/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/e2b/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/e2b/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/e2b/framework/cli)
- [Google ADK](https://composio.dev/toolkits/e2b/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/e2b/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/e2b/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/e2b/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/e2b/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for E2b
- Connect LlamaIndex to the E2b MCP server
- Build a E2b-powered agent using LlamaIndex
- Interact with E2b through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## What is the E2b MCP server, and what's possible with it?

The E2b MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your E2b account. It provides structured and secure access so your agent can perform E2b operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `E2B_CONNECT_SANDBOX` | Connect to Sandbox | Tool to connect to an existing E2B sandbox and retrieve its details. Use when you need to reconnect to a sandbox from different environments or resume a paused sandbox. The TTL is extended upon connection. |
| `E2B_CREATE_TEMPLATE` | Create Template | Tool to create a new E2B template with specified configuration. Use when you need to define a new sandbox template that can be used to spawn sandbox environments. |
| `E2B_CREATE_WEBHOOK` | Create Webhook | Tool to register a new webhook to receive sandbox lifecycle events for the team. Use when you need to set up notifications for sandbox lifecycle events such as creation, updates, or termination. |
| `E2B_DELETE_SANDBOXES` | Delete Sandbox | Tool to terminate and permanently delete a running E2B sandbox instance. Use when you need to kill a sandbox that is no longer needed. Once terminated, the sandbox cannot be resumed. |
| `E2B_DELETE_WEBHOOK` | Delete Webhook | Tool to unregister a webhook and stop receiving lifecycle events. Use when you need to remove a webhook that is no longer needed or to clean up webhook registrations. |
| `E2B_CHECK_API_HEALTH` | Check API Health | Tool to check the health status of the E2B API. Use when you need to verify that the API service is operational and accessible. |
| `E2B_GET_SANDBOX` | Get Sandbox | Tool to retrieve detailed information about a specific sandbox by its ID. Use when you need to check sandbox status, metadata, or configuration details. |
| `E2B_GET_SANDBOX_LOGS` | Get Sandbox Logs | Tool to retrieve logs from a specific E2B sandbox instance. Use when you need to debug or monitor sandbox execution by viewing its console output and system logs. |
| `E2B_GET_SANDBOX_LIFECYCLE_EVENTS` | Get Sandbox Lifecycle Events | Tool to retrieve the latest lifecycle events for a particular sandbox instance. Use when you need to track state changes including creation, pausing, resuming, updates, and termination of a sandbox. |
| `E2B_GET_SANDBOX_METRICS` | Get Sandbox Metrics | Tool to retrieve timestamped CPU, memory, and disk usage metrics for a sandbox. Use when you need to monitor resource usage of a running sandbox. Metrics are collected every 5 seconds; returns empty array if no metrics available yet. |
| `E2B_GET_TEAM_METRICS` | Get Team Metrics | Tool to retrieve timestamped CPU, memory, and disk usage metrics for a team. Use when you need to monitor aggregated resource usage across all sandboxes belonging to a team. |
| `E2B_GET_TEAM_MAXIMUM_METRICS` | Get Team Maximum Metrics | Tool to retrieve the maximum value for a specific team metric in a given interval. Use when you need to check team limits or peak usage, such as maximum concurrent sandboxes allowed or highest resource usage. |
| `E2B_GET_TEMPLATE_BUILD_STATUS` | Get Template Build Status | Tool to get the status of a template build. Use when you need to check the build status of a template that was started asynchronously. Useful in polling loops to monitor template builds in progress. |
| `E2B_GET_TEMPLATE_FILES` | Get Template Files | Tool to get an upload link for a tar file containing build layer files. Use when you need to retrieve or download template build layer files by their hash. |
| `E2B_GET_WEBHOOK_CONFIGURATION` | Get Webhook Configuration | Tool to retrieve the current webhook configuration for a specific webhook. Use when you need to inspect webhook settings, verify configuration, or check webhook status. |
| `E2B_LIST_ALL_SANDBOXES` | List All Sandboxes | Tool to list all running and paused sandboxes associated with your team. Use when you need to view active sandboxes, monitor sandbox state, or retrieve sandbox identifiers for further operations. Supports pagination and filtering by state or metadata. |
| `E2B_LIST_SANDBOXES_METRICS` | List Sandboxes Metrics | Tool to retrieve timestamped CPU, memory, and disk usage metrics for multiple sandboxes. Use when you need to monitor resource usage across multiple sandboxes simultaneously. Metrics are collected every 5 seconds; returns empty array if no metrics available yet. |
| `E2B_LIST_TEAM_SANDBOX_LIFECYCLE_EVENTS` | List Team Sandbox Lifecycle Events | Tool to retrieve the latest lifecycle events across all sandboxes associated with the team. Use when you need to monitor sandbox activity, track lifecycle changes, or audit sandbox operations. |
| `E2B_LIST_ALL_TEMPLATES` | List All Templates | Tool to list all available E2B templates for your team. Use when you need to view available templates, retrieve template identifiers, or audit template configurations. |
| `E2B_LIST_ALL_WEBHOOKS` | List All Webhooks | Tool to retrieve all registered webhooks for your team. Use when you need to view all webhook configurations, audit webhook settings, or manage multiple webhooks. |
| `E2B_PAUSE_SANDBOX` | Pause Sandbox | Tool to pause a running E2B sandbox preserving its filesystem and memory state. Use when you need to temporarily suspend a sandbox while maintaining its state for later resumption. Takes approximately 4 seconds per 1 GiB of RAM to pause. Paused sandboxes can be stored for up to 30 days. |
| `E2B_CREATE_SANDBOX` | Create Sandbox | Tool to create a new E2B sandbox from a template. Use when you need to launch a fresh sandbox environment for code execution, testing, or development purposes. |
| `E2B_SET_SANDBOX_TIMEOUT` | Set Sandbox Timeout | Tool to set the timeout for an E2B sandbox. Use when you need to extend or reduce the sandbox lifetime. The timeout is measured from the current time, and calling this multiple times overwrites the previous TTL. |
| `E2B_REFRESH_SANDBOX` | Refresh Sandbox | Tool to refresh an E2B sandbox and extend its time to live. Use when you need to keep a sandbox alive longer and prevent it from timing out. |
| `E2B_START_TEMPLATE_BUILD` | Start Template Build | Tool to start a build for an E2B template. Use when you need to initiate the build process for a template with specific configuration. The build runs asynchronously and returns immediately with a 202 Accepted status. |
| `E2B_UPDATE_TEMPLATE` | Update Template | Tool to update an E2B template configuration. Use when you need to modify template settings such as changing visibility (public/private status). |
| `E2B_UPDATE_WEBHOOK_CONFIGURATION` | Update Webhook Configuration | Tool to update an existing webhook configuration including URL, enabled status, and subscribed events. Use when you need to modify webhook settings, change the destination URL, enable/disable a webhook, or update event subscriptions. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The E2b MCP server is an implementation of the Model Context Protocol that connects your AI agent to E2b. It provides structured and secure access so your agent can perform E2b operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A E2b account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and E2b

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for E2b access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, e2b)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available E2b tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["e2b"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform E2b actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform E2b actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["e2b"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform E2b actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to E2b
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with E2b, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["e2b"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform E2b actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform E2b actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["e2b"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform E2b actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected E2b to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes E2b tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build E2b MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/e2b/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/e2b/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/e2b/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/e2b/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/e2b/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/e2b/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/e2b/framework/codex)
- [Cursor](https://composio.dev/toolkits/e2b/framework/cursor)
- [VS Code](https://composio.dev/toolkits/e2b/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/e2b/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/e2b/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/e2b/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/e2b/framework/cli)
- [Google ADK](https://composio.dev/toolkits/e2b/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/e2b/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/e2b/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/e2b/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/e2b/framework/crew-ai)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and E2b MCP?

With a standalone E2b MCP server, the agents and LLMs can only access a fixed set of E2b tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from E2b and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right E2b tools.

### Can I manage the permissions and scopes for E2b while using Tool Router?

Yes, absolutely. You can configure which E2b scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your E2b data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)