Skip to main content
Glama
gbatistuta0

AppFactory

by gbatistuta0
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

AI Deploy Proxy

ai_deploy_proxy
DestructiveIdempotent

Deploys an app's AI backend: spec-driven subscription mode or legacy credits proxy, storing keys in server-side secrets and requiring human approval for live changes.

Instructions

Deploy the AI backend: the full spec-driven backend in subscription mode, or the legacy ai-proxy in credits mode (live, needs human approval).

Use when: the app has an AI feature. AI keys go only to server-side secrets. For explicit dry-run planning use backend_deploy. Returns: {ok, deployed: [...]} or an approval_required refusal.

Input Schema

NameRequiredDescriptionDefault
app_dirYesAbsolute path to the app project directory (contains app.spec.json), e.g. /Users/me/Apps/MyApp.
approval_idNoApproval id from a previous approval_required refusal; omit on the first call. The human approves out-of-band with `appfactory approve <id>`, then call again with the same arguments and this id.
daily_limitNoPer-user daily request cap for the legacy ai-proxy (default 20).
project_refYesSupabase project ref to deploy to.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.5
    • addedInput schema / properties / app_dir / description
      Added value: +"Absolute path to the app project directory (contains app.spec.json), e.g. /Users/me/Apps/MyApp."
    • addedInput schema / properties / approval_id / description
      Added value: +"Approval id from a previous approval_required refusal; omit on the first call. The human approves out-of-band with `appfactory approve <id>`, then call again with the same arguments and this id."
    • addedInput schema / properties / daily_limit / description
      Added value: +"Per-user daily request cap for the legacy ai-proxy (default 20)."
    • addedInput schema / properties / project_ref / description
      Added value: +"Supabase project ref to deploy to."
  2. First observedv0.1.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations cover the safety profile (destructive, idempotent, open-world), but the description adds genuinely new behavior: credits mode is 'live, needs human approval', keys go only to server-side secrets, and the call can return an approval_required refusal. It does not explain what idempotency means here or the effect of re-deploying over an existing backend.

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

Conciseness5/5

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

Front-loaded with the action, then 'Use when', then 'Returns' – three tight segments with no filler. Every sentence earns its place.

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

Completeness4/5

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

Output schema exists and the return shape is restated, and the approval workflow is covered. Remaining gap: nothing explains how the subscription vs. legacy mode is chosen or how daily_limit relates to mode, which is the key ambiguity for this tool.

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

Parameters3/5

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

Schema description coverage is 100%, including the detailed approval_id round-trip and the daily_limit default, so the schema carries the parameter burden. The description adds no per-parameter meaning beyond that, so a baseline 3 is appropriate.

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 specific verb+resource ('Deploy the AI backend') and explicitly splits it into two modes (spec-driven subscription mode vs. legacy ai-proxy in credits mode), which lets an agent tell it apart from backend_render and backend_deploy without opening a 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 a clear positive trigger ('Use when: the app has an AI feature') and routes dry-run planning to backend_deploy explicitly. It stops short of stating when NOT to use it (e.g. when a deployment already exists) or how the two modes are selected.

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

Deploy Server

Other Tools