E2b MCP integration
Launches sandboxes from templates, reads their logs and resource metrics, pauses one to preserve state, and kills the instances nobody is using.
27actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Create sandbox
Lyro creates a new E2B sandbox from a template. Support teams spin up isolated testing environments instantly for debugging and development tasks.
Pause sandbox
Lyro pauses a running E2B sandbox preserving its filesystem and memory state. Agents manage compute costs while preserving work in progress.
Start template build
Lyro starts a build for an E2B template. Support teams automate environment setup and deployment pipelines from the conversation.
How businesses use E2b + Lyro
Each card is one request a support team gets, and the E2b actions Lyro runs to close it.
Launch a sandbox from the right template
Lyro lists the templates the team owns, spins a fresh sandbox from the one that fits, and reconnects to an existing sandbox when work should resume rather than start over.
List All TemplatesCreate SandboxConnect to SandboxSee what a sandbox is doing and what it uses
Lyro pulls console output and system logs from a sandbox, its CPU, memory, and disk metrics sampled every five seconds, and the team-wide totals when the question is about overall consumption.
Get Sandbox LogsGet Sandbox MetricsGet Team MetricsKeep sandboxes alive only as long as they earn it
Lyro extends a sandbox's time to live while work is still running, pauses one to preserve its filesystem and memory state, and terminates the instances sitting idle across the team.
Set Sandbox TimeoutPause SandboxDelete SandboxTrack a template build and its lifecycle events
Lyro starts an asynchronous template build and polls it to completion, registers a webhook for sandbox creation, update, and termination events, and reads the lifecycle trail across the whole team.
Start Template BuildGet Template Build StatusCreate Webhook
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the E2b actions it has and picks the ones a request needs.
Connect E2b
Authorize the E2b account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the E2b actions that close it and chains as many as the request needs.
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
E2b · Lyro
What can you do in E2b without me setting anything up?
These, right away:
- Create template
- Check API health
- Delete sandbox
Great, let's start with the first one.
FAQ
Everything else about E2b
Setup, permissions, and the limits of what Lyro can do inside E2b.
Up to 30 days. Pause Sandbox preserves filesystem and memory state and takes roughly four seconds per GiB of RAM, and Connect to Sandbox resumes it while extending its TTL. Delete Sandbox is the opposite end: once terminated, that instance cannot be brought back.
Every action available in E2b
All 27 actions your agent can call on E2b, straight from the live MCP connection.
Connect to sandbox
Connect to an existing E2B sandbox and retrieve its details.
Create template
Create a new E2B template with specified configuration.
Create webhook
Register a new webhook to receive sandbox lifecycle events for the team.
Delete sandbox
Terminate and permanently delete a running E2B sandbox instance.
Delete webhook
Unregister a webhook and stop receiving lifecycle events.
Check API health
Check the health status of the E2B API.
Get sandbox
Retrieve detailed information about a specific sandbox by its ID.
Get sandbox logs
Retrieve logs from a specific E2B sandbox instance.
Get sandbox lifecycle events
Retrieve the latest lifecycle events for a particular sandbox instance.
Get sandbox metrics
Retrieve timestamped CPU, memory, and disk usage metrics for a sandbox.
Get team metrics
Retrieve timestamped CPU, memory, and disk usage metrics for a team.
Get team maximum metrics
Retrieve the maximum value for a specific team metric in a given interval.
Get template build status
Get the status of a template build.
Get template files
Get an upload link for a tar file containing build layer files.
Get webhook configuration
Retrieve the current webhook configuration for a specific webhook.
List all sandboxes
List all running and paused sandboxes associated with your team.
List sandboxes metrics
Retrieve timestamped CPU, memory, and disk usage metrics for multiple sandboxes.
List team sandbox lifecycle events
Retrieve the latest lifecycle events across all sandboxes associated with the team.
List all templates
List all available E2B templates for your team.
List all webhooks
Retrieve all registered webhooks for your team.
Pause sandbox
Pause a running E2B sandbox preserving its filesystem and memory state.
Create sandbox
Create a new E2B sandbox from a template.
Set sandbox timeout
Set the timeout for an E2B sandbox.
Refresh sandbox
Refresh an E2B sandbox and extend its time to live.
Start template build
Start a build for an E2B template.
Update template
Update an E2B template configuration.
Update webhook configuration
Update an existing webhook configuration including URL, enabled status, and subscribed events.
The tools E2b sits next to
Same connection, same setup. Pick the next one your team already uses.
Appdrag
Calls Cloud Backend functions on prod, preprod, or dev with the verb they expect, and runs Visual SQL reads, updates, and deletes on the Cloud DB.
Cloudflare browser rendering
Cloudflare Browser Rendering lets you programmatically control headless browsers running on Cloudflare’s global network.
Doppler secretops
Pulls config audit trails, creates projects and branch configs, locks what must not change, and rolls a bad config back to an earlier version.
Launch darkly
Checks flag status by environment, evaluates what a specific user is actually served, and routes flag changes through approval instead of flipping them directly.
Render
Reports deploy status and logs, triggers deploys and restarts, updates environment variables and secret files, and pulls CPU, memory, and connection metrics.
Triggercmd
Lists the machines and commands on a TriggerCMD account, then fires a named command or panel button on the computer you specify.
Ready to connect E2b?
Authorize the account and your agent has all 27 actions from the first conversation.