Sprites

Give your AI agent a persistent, hardware-isolated Linux sandbox it can create, run commands in, checkpoint and destroy.

Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.

Paste it into any MCP client. Setup docs

What the Sprites connector does

The Sprites MCP server connects Fly.io's code sandboxes to Claude, ChatGPT and any MCP-compatible agent. It exposes 18 tools that create a persistent Linux microVM, run shell commands inside it, snapshot and roll back its filesystem, manage background services, and rewrite its outbound network policy. Sign-in is OAuth, and the default token only reaches Sprites the connector itself created.

Verified connector

Listed by Anthropic as a partner connector in its Connectors Directory.

Connection checked by Agentman on .

Anthropic states this reflects the level of review a connector received, not a security audit.

Sprites tools (18)

  • checkpoint_create
  • checkpoint_get
  • checkpoint_list
  • checkpoint_restore
  • create_sprite
  • destroy_sprite
  • exec
  • exec_kill
  • exec_list
  • list_sprites
  • policy_network_get
  • policy_network_update
  • service_create
  • service_get
  • service_list
  • service_logs
  • service_start
  • service_stop

Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.

Frequently asked questions

Can the Sprites MCP connector run arbitrary code on my machine?

No. The exec tool runs commands inside a Sprite, which Fly.io describes as a hardware-isolated Firecracker microVM in its cloud, not on your computer. Nothing executes locally, and the connector reaches only Sprites owned by the Fly.io organization you pick during the OAuth flow.

What can a Sprite reach on the network by default?

Anything. Sprites documents outbound access as unrestricted by default, so a fresh Sprite can resolve and reach any domain. Tightening it is opt-in through a network policy, a DNS-based allowlist applied from outside the Sprite. The policy_network_update tool is how the connector applies that restriction.

Can the connector make my code publicly reachable on the internet?

Not by itself. Every Sprite has an HTTPS URL, but Sprites documents it as private by default and reachable only by members of your organization. Switching a URL to public is a separate sprite config update command, and no tool in the connector's 18 published names performs that switch.

Is destroying a Sprite reversible?

No. Sprites states plainly that destroy_sprite permanently deletes a Sprite and its data with no undo. Checkpoints protect against a bad command inside a surviving Sprite, not against the Sprite being removed. Restrict the connector token to a name prefix so it can only reach Sprites you created for it.

What does a checkpoint actually save?

The writable filesystem overlay. Sprites lists files, directories, installed packages, config files and on-disk databases as captured, and running processes, in-memory state and open network connections as not captured. Restoring replaces your current filesystem with the saved one, and the state you overwrite is not backed up for you.

Can I stop the connector from touching my existing Sprites?

Yes, and the default already does. Sprites issues a restricted token that can only create Sprites whose names begin with mcp- and caps how many. The consent screen lets you change the prefix, raise or lower the cap, or switch to full access across the organization. Sprites recommends staying restricted.

Does creating Sprites through Claude cost money?

Yes, while they run. Sprites bills compute per second and only while a Sprite is active, so an idle Sprite costs no compute. Storage is billed on bytes actually written against a 100 GB per-Sprite ceiling, and kept checkpoint blocks bill separately. Fly.io publishes no pricing page in the Sprites documentation.

Why does a tool call fail while a Sprite is starting?

The Sprite was cold and is still waking. Sprites documents cold wakes as taking one to two seconds, and its troubleshooting tells you to wait a few seconds and run the same tool again. A warm Sprite resumes in 100 to 500 milliseconds instead, with running processes preserved.

Sources

Use it in an agent

Put Sprites to work.

Connect Sprites once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.

Call (650) 285-1019, Agentman.Our AI receptionist answers.