Local MCP

Image Playground Generate

image_playground_generate

Destructive

Generates an image on the Mac from a text prompt with Apple's Image Playground model (Apple Intelligence; no API key needed). Saves a PNG and reveals it in Finder so the user can see it and drag it anywhere. Styles are Apple's built-in set (animation, illustration, sketch) — good for quick stylized art, NOT photorealistic. Requires macOS 15.4+ with Apple Intelligence enabled. On macOS 15.x/26 generation is fully automatic; on macOS 27+ a small Image Playground panel opens and the user clicks the image once to save it (Apple's public API on that version). WHERE TO SAVE: if the user names a place (e.g. "my Desktop", "the project folder"), pass that as output_path; otherwise omit it and it lands in ~/Pictures/Image Playground/ with a name from the prompt, then opens in Finder.

Input Schema

Name	Required	Description
`style`	No	Visual style. Default 'animation'. Falls back to an available style if the requested one isn't supported on this device.
`prompt`	Yes	Text description of the image to generate.
`confirm`	No	Ignored; kept for older clients.
`output_path`	No	Where to save the PNG — an absolute path or ~ path (a file like ~/Desktop/art.png, or a folder to save into). Omit to use ~/Pictures/Image Playground/<prompt>-<timestamp>.png. Missing parent folders are created.
`reveal_in_finder`	No	Open Finder with the new image selected so the user can see/move it. Default true; set false when generating many in a row.

Output Schema

Name	Required	Description	Default
`path`	Yes
`style`	Yes
`width`	Yes
`engine`	Yes
`height`	Yes
`prompt`	Yes
`created`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

changedInput schema / properties / confirm / description

Previous value: -"Must be true to generate and save the image. Without it the call returns a preview and creates nothing."New value: +"Ignored; kept for older clients."

Changed1 schema field changedOct 22, 2026

addedInput schema / properties / confirm

Added value: +{
+  "description": "Must be true to generate and save the image. Without it the call returns a preview and creates nothing.",
+  "type": "boolean"
+}

AddedOct 20, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Adds real behavioral context beyond annotations: no API key needed, requires macOS 15.4+ with Apple Intelligence, different flow per macOS version, and the side effect of opening Finder. It does not disclose what happens if output_path already exists (overwrite vs. fail), which is the main reason destructiveHint=true would matter to an agent deciding whether to confirm with the user.

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 and model, then prerequisites, then a clearly labeled WHERE TO SAVE block. It is on the longer side, but nearly every sentence carries operational information; only the version-comparison detail could be trimmed.

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?

Given an output schema exists, the description needn't describe return values, and it covers what remains: OS prerequisites, the human-in-the-loop panel on newer macOS, default save location, and the Finder reveal side effect. Nothing needed 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 adds decision-level meaning: when to supply output_path versus omit it, and where the default lands. It also tells the agent that 'confirm' is ignored, steering it away from a parameter the schema still exposes.

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 ('Generates an image... from a text prompt with Apple's Image Playground model') and pins the scope tightly: stylized built-in styles, explicitly NOT photorealistic. No sibling tool generates images, so differentiation is implicit but the stated capability boundary makes the tool unambiguously identifiable.

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

Usage Guidelines5/5

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

Gives explicit inclusion criteria (quick stylized art) and exclusion criteria ('NOT photorealistic'), plus a concrete decision rule for output_path: pass a path only if the user names a place, otherwise omit it. It also flags the macOS 27+ case where the user must click the image once, so the agent can set expectations.

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

All Local MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.