Sprites provides persistent, isolated cloud environments for running code and AI-generated applications. Create and manage sandboxed Linux machines, execute commands, install dependencies, host services, persist files across sessions, and checkpoint or restore environments for reproducible development and testing.
Codex is OpenAI's coding agent for the terminal. It reads MCP servers from its config and signs in to remote ones with OAuth.
This guide connects Sprites MCP to Codex through MewCP, so Codex can use Sprites MCP's 27 tools, like list_sprites, create_sprite and destroy_sprite, without your Sprites MCP credentials ever reaching the app.
Sprites MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
More apps
Manage repositories, pull requests, issues, branches and development workflows on GitHub. Automate software delivery and collaborate across engineering projects.
Connect to external APIs, webhooks and internet services through standard HTTP requests. Build integrations with virtually any platform that exposes a web-based interface.
Give AI coding agents access to a curated library of real-world website designs, screenshots, design systems, and reusable UI components. Search visual references, find similar designs, analyze layouts, extract colors and typography, compare websites, and retrieve copy-ready JSX components for building better interfaces
HotAPI provides a unified API for AI-powered image, video, and audio generation, image editing, and conversational AI. Developers can access multiple models through a single API key, track asynchronous generation tasks, and retrieve results with polling or webhooks.
Other clients
Sprites MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Sprites MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Run this and approve access in the browser window.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
List sprites for the authenticated organization.
Create a new sprite in the authenticated organization.
Destroy a sprite in the authenticated organization.
Find up to 20 authorized Sprites by name prefix for composer mentions.
Open a read-only Sprite Inspector showing environments, services, checkpoints and recent service logs. Opening only lists metadata; runtime reads are explicit and may wake a Sprite.
Read authorized Sprite metadata without waking it. Pass sprite_id from a mention or Inspector selection to reject deleted and recreated environments.
List active exec sessions.
Execute a command via simple HTTP POST (non-TTY only). Simpler alternative for exec for environments that can't handle websockets.
Kill an exec session by session ID. Returns streaming NDJSON with kill progress.
Create a new checkpoint of the current sprite state. Returns streaming NDJSON progress.
List all checkpoints.
Get details of a specific checkpoint.
Restore to a specific checkpoint. Returns streaming NDJSON progress.
Get the current network policy configuration. A Sprite with no rules (the default) reaches the public internet.
Update the network policy configuration. Available to every organization. Rules restrict the Sprite to the domains and addresses they allow; an empty rule list restores public internet access.
List all configured services and their current state.
Get details of a specific service.
Create or update a service definition.
Start a service. Returns streaming NDJSON with stdout/stderr.
Stop a running service. Returns streaming NDJSON with service stop progress.
Stream logs for a service.
Read file contents from the sprite filesystem. Returns raw file bytes.
Write up to 16 MiB of file contents to the sprite filesystem. Request body contains raw file bytes.
List directory contents.
Delete a file or directory.
Rename or move a file or directory.
Copy a file or directory.
