Developer Tools & DevOps

Connect E2B to Your AI Agents

Enable your Wkil agents to create, run, and manage isolated code sandboxes through a secure E2B integration.

Authentication: API key

Build with E2B

What you can do

Spin up isolated code sandboxes on demand
Run and inspect code execution logs
Manage sandbox lifecycle and resources

Available capabilities may vary by authentication and workspace configuration.

Actions supported by the connector

27 verified tools

Create Sandbox

Start a new isolated code-execution sandbox.

Connect to Sandbox

Connect to an existing running sandbox.

Get Sandbox Logs

Retrieve execution logs from a sandbox.

List All Sandboxes

List currently running or recent sandboxes.

Delete Sandbox

Terminate and remove a running sandbox.

Pause Sandbox

Pause a running sandbox without deleting it.

Set Sandbox Timeout

Change how long a sandbox stays alive before it auto-terminates.

Create Template

Define a reusable sandbox template.

Get Sandbox Metrics

Retrieve resource usage metrics for a sandbox.

Create Webhook

View all verified tools (search)

Connect to SandboxCreate TemplateCreate WebhookDelete SandboxDelete WebhookCheck API HealthGet SandboxGet Sandbox LogsGet Sandbox Lifecycle EventsGet Sandbox MetricsGet Team MetricsGet Team Maximum MetricsGet Template Build StatusGet Template FilesGet Webhook ConfigurationList All SandboxesList Sandboxes MetricsList Team Sandbox Lifecycle EventsList All TemplatesList All WebhooksPause SandboxCreate SandboxSet Sandbox TimeoutRefresh SandboxStart Template BuildUpdate TemplateUpdate Webhook Configuration

Practical agent use cases

An agent spins up a sandbox to safely run and test generated code before returning results.
An agent retrieves sandbox logs to diagnose why a code run failed.

How it works with Wkil

1
Choose the integration
Add E2B to your agent from inside the Wkil platform.
2
Grant the permissions it needs
Define precisely what the agent can access and perform.
3
Test, then run it
Test actions before they go live, with human approval where needed.

Permissions always stay in your control — you can scope access and require human approval before any sensitive action.

Related integrations

FAQ

Is code execution isolated from our production systems?

Yes — each sandbox is an isolated execution environment separate from your production infrastructure.