> ## Documentation Index
> Fetch the complete documentation index at: https://e2b.manicule.dev/llms.txt
> Use this file to discover all available pages before exploring further.
> For every page in one file, fetch https://e2b.manicule.dev/llms-full.txt (large).
> To search and read these docs as tools, connect the MCP server at https://e2b.manicule.dev/api/mcp.
> Every agent surface: https://e2b.manicule.dev/.well-known/llms-manifest.json

# Custom templates (/docs/mcp/custom-templates)

<!-- agent-signals: reading_time_min: 2 · est_tokens: 772 · updated: 2026-07-30 -->
Related: [Available servers](/docs/mcp/available-servers.md), [Custom servers](/docs/mcp/custom-servers.md), [Examples](/docs/mcp/examples.md), [Quickstart](/docs/mcp/quickstart.md)

> Use MCP servers with custom sandbox templates

You can prepull MCP server Docker images during template build time to significantly improve runtime performance.

## How it works

When you build a template with prepulled MCP servers, the Docker images for those servers are downloaded and cached during the build process. This means when you create a sandbox from that template, the MCP servers are ready to use immediately without waiting for image downloads.

<Info>You must use the MCP gateway enabled template (`mcp-gateway`) as your base template to use this feature.</Info>

## Building a template with MCP servers

Use the `addMcpServer()` method (TypeScript) or `add_mcp_server()` method (Python) to prepull MCP server images during template build. You can pass a single server or an array of servers.

The server names (like `"browserbase"` and `"exa"`) correspond to the keys defined in the [Available Servers](/docs/mcp/available-servers) documentation.

<CodeGroup>
```typescript title="JavaScript & TypeScript"
import "dotenv/config";
import { Template, defaultBuildLogger } from 'e2b';

export const template = Template()
  .fromTemplate("mcp-gateway")
  .addMcpServer(["browserbase", "exa"]);

await Template.build(template, 'my-mcp-gateway', {
  cpuCount: 8,
  memoryMB: 8192,
  onBuildLogs: defaultBuildLogger(),
});
```

```python title="Python"
from dotenv import load_dotenv
from e2b import Template, default_build_logger

load_dotenv()

template = (
    Template()
    .from_template("mcp-gateway")
    .add_mcp_server(["browserbase", "exa"])
)

Template.build(
    template,
    'my-mcp-gateway',
    cpu_count=8,
    memory_mb=8192,
    on_build_logs=default_build_logger(),
)
```
</CodeGroup>

## Using the template

Once built, create sandboxes from your template. You still need to provide the configuration for each MCP server.

<CodeGroup>
```typescript title="JavaScript & TypeScript"
import { Sandbox } from 'e2b';

const sandbox = await Sandbox.create({
    template: "my-mcp-gateway",
    mcp: {
        browserbase: {
            apiKey: process.env.BROWSERBASE_API_KEY!,
            geminiApiKey: process.env.GEMINI_API_KEY!,
            projectId: process.env.BROWSERBASE_PROJECT_ID!,
        },
        exa: {
            apiKey: process.env.EXA_API_KEY!,
        },
    },
});

```

```python title="Python"
from e2b import Sandbox
import os

sbx = Sandbox.create(
    template="my-mcp-gateway",
    mcp={
        "browserbase": {
            "apiKey": os.getenv("BROWSERBASE_API_KEY"),
            "geminiApiKey": os.getenv("GEMINI_API_KEY"),
            "projectId": os.getenv("BROWSERBASE_PROJECT_ID"),
        },
        "exa": {
            "apiKey": os.getenv("EXA_API_KEY"),
        },
    }
)
```
</CodeGroup>

## Learn more

For more information about working with templates, see:

* [Template Quickstart](/docs/template/quickstart) - Get started with custom templates
* [Defining Templates](/docs/template/defining-template) - Learn all template configuration options
* [Template Build](/docs/template/build) - Understand the build process