fuast

Deploy an app

deploy_app

Destructive

Deploys the files and returns the app's URL. With a connected fuast account it creates a new private app in the person's workspace, or updates the app named in app. Without an account it deploys a temporary preview and returns preview_url, claim_url and edit_token: give the person claim_url so they can make the app theirs, and pass edit_token to later calls to keep working on it. Send every file each time; use update_app_files to change a few. A failed build returns diagnostics with file and line and deploys nothing.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "files": "<files>"
    },
    "name": "deploy_app"
  }
}

Input Schema

Name	Required	Description
`app`	No	Slug of an existing app in the connected account to update. Leave out to create a new app.
`name`	No	Name of a new app. Its address is derived from it. Ignored when updating an app.
`files`	Yes	The whole app as {"relative/path": "file content"}. server/index.ts and client/index.tsx are required. Text files only (.ts .tsx .js .jsx .mjs .json .md .svg .txt .css .html).
`edit_token`	No	To update a preview that was deployed without an account: the edit_token that deploy returned.
`delete_tables`	No	Only when a deploy was refused because the new schema drops tables that hold rows: repeat each table with the exact row count from that error to confirm deleting it.

Output Schema

Name	Required	Description	Default
`url`	Yes
`name`	No
`slug`	Yes
`limits`	No
`created`	No
`manifest`	No
`claim_url`	No
`deploy_id`	Yes
`trust_url`	No
`unclaimed`	Yes
`edit_token`	No
`expires_at`	No
`next_steps`	Yes
`restricted`	No
`visibility`	No
`preview_url`	No
`trust_command`	No
`restricted_hint`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: create-vs-update semantics, the anonymous preview returning preview_url/claim_url/edit_token, token propagation to later calls, and the important failure trait that "a failed build returns diagnostics with file and line and deploys nothing." It does not explain what makes the operation destructive (destructiveHint=true), e.g., that redeploying an existing app overwrites its files or that schema changes can drop tables, which is only inferable from the delete_tables parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose in the first clause, then branches by mode, then ends on the failure contract; nearly every sentence carries callable information. The middle token-handling sentence is long and packs two instructions (give claim_url, retain edit_token) into one breath, which costs some clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter, branching, mutating tool with an output schema and full annotation coverage, the description supplies what the structured fields cannot: the account/no-account split, the token handoff protocol, and the atomic failure guarantee. Little an agent needs in order to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds meaning: app selects update-in-place versus create, name is ignored when updating, edit_token is what you must pass back to keep editing a preview, and files must be the complete set every time. delete_tables is left entirely to the schema, which prevents a higher score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb+resource ("Deploys the files and returns the app's URL") and immediately splits the two operating modes: create/update with a connected account versus anonymous temporary preview. An agent can distinguish it from update_app_files and check_app without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit alternative with its selection condition: "Send every file each time; use update_app_files to change a few," plus the preview flow instructions for claim_url and edit_token. It does not cover other adjacent choices (e.g., verifying with check_app before or after, or when to prefer rollback_app), but the primary division of labor is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All fuast tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?