Daytona
Enable agents to provision and manage isolated Daytona sandboxes. Run code, execute commands, manage files, and integrate with Git in secure environments.
Available Tools
46 tools available in this integration
Daytona.ArchiveSandbox Archive a stopped sandbox to reduce storage costs
Daytona.ConfigureSandboxAuto Configure auto-stop, auto-archive, and/or auto-delete intervals
Daytona.CreateFolder Create a folder (with parent directories) in the sandbox
Daytona.CreateSandbox Create a new isolated sandbox for code execution
Daytona.CreateSession Create a persistent background session for long-running processes
Daytona.CreateSnapshot Create a new sandbox snapshot (image template)
Daytona.CreateSshAccess Create SSH access credentials for the sandbox
Daytona.DeleteFile Delete a file or empty directory
Daytona.DeleteSandbox Permanently delete a sandbox and all its contents
Daytona.FindFiles Search for files by name pattern (glob)
Daytona.GetFileInfo Get metadata about a file: size, permissions, modified time, type
Daytona.GetPortPreviewUrl Get a preview URL for a web service running in the sandbox
Daytona.GetSandbox Get detailed information about a sandbox
Daytona.GetSessionCommandLogs Get output logs from a command running in a session
Daytona.GetSnapshot Get detailed information about a snapshot
Daytona.GitAdd Stage files for the next commit
Daytona.GitBranches List all branches and indicate which is currently checked out
Daytona.GitCheckout Switch to a branch, tag, or commit
Daytona.GitClone Clone a Git repository into the sandbox
Daytona.GitCommit Commit staged changes
Daytona.GitCreateBranch Create a new branch and switch to it
Daytona.GitDeleteBranch Delete a local branch
Daytona.GitLog Get commit history with hash, author, date, and message
Daytona.GitPull Pull latest changes from the remote repository
Daytona.GitPush Push local commits to the remote repository
Daytona.GitStatus Get repository status: branch, staged/modified/untracked files
Daytona.ListFiles List files and directories with metadata
Daytona.ListPorts List active ports in the sandbox
Daytona.ListRegions List available regions for sandbox creation
Daytona.ListSandboxes List sandboxes with optional filtering and pagination
Daytona.ListSessions List all active sessions in a sandbox
Daytona.ListSnapshots List available snapshots with status and creation date
Daytona.MoveFile Move or rename a file or directory
Daytona.ReadFile Read file contents from the sandbox
Daytona.ReplaceInFiles Find and replace text across multiple files
Daytona.ResizeSandbox Resize sandbox resources (CPU, memory, disk)
Daytona.RunCode Execute code directly in the sandbox
Daytona.RunCommand Execute a shell command in the sandbox
Daytona.RunSessionCommand Execute a command inside an existing session
Daytona.SearchContent Search file contents for a text pattern
Daytona.SendSessionInput Send input to a running interactive command in a session
Daytona.SetSandboxLabels Replace all labels on a sandbox
Daytona.StartSandbox Start a stopped or archived sandbox
Daytona.StopSandbox Stop a running sandbox, preserving its state for later restart
Daytona.WhoAmI Get the authenticated user's profile
Daytona.WriteFile Write content to a file in the sandbox
Why agent-optimized tools matter
Built for intent, not API schemas
Forcing the agent to juggle not only what you want to get done, but also how to operate all the APIs it needs to use is a recipe for disaster. Agent-optimized tools keep the agent focused on the work at hand, not ID hunting.
Up to 100x fewer tokens
Context bloat is a serious problem that gets in the way of real work getting done with agents. Agent-optimized tools return only the fields the agent needs to get the job done, not the full API response. Up to 100x less token consumption on every call.
Coverage for the whole task
Most tasks take more than one action to finish. Agent-optimized tools cover the full sequence so the agent completes the workflow end to end, not just the first lookup.
Consistent at scale
Agent-optimized tools behave the same across every user, every run, every harness, every model, and every effort level. No need for the agent to spend time and tokens re-learning the API shape, it can focus on the task at hand. What works for one user holds up when serving thousands in production.
Your questions, answered
It's built around what an agent is trying to accomplish rather than mirroring Daytona's raw API. Fewer required parameters, far fewer tokens per call, and coverage for the whole task — so agents succeed more often.
Yes. The toolkit is exposed over an MCP gateway that any framework or MCP client can connect to, and we publish install guides for the editors and coding agents we document.
No. Arcade proxies API calls and does not persist your Daytona content. Where Daytona requires credentials, Arcade brokers them and stores them encrypted at rest — the model never sees them.
With Contextual Access policies: require human approval before consequential actions, redact sensitive fields on the way back, or restrict the scopes a given agent gets.
