apple-image-mcp
On-device AI image generation for macOS with 17 tools and zero API keys, combining Apple Intelligence and Pollinations for stylized and photorealistic images, auto-cropping for 40+ social media platforms.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
vakandi
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
list_enginesList available image generation engines. Apple Image Playground runs fully on-device via Shortcuts.app — no API keys, no cloud calls.
list_presetsList all 40+ social media / blog / web output size presets with dimensions.
list_bundlesList predefined bundles — groups of presets for common use cases.
list_stylesList all available Apple Image Playground styles from the ImagePlayground API.
generate_imageGenerate an image using Apple Image Playground via Shortcuts.app. Fully on-device — no API keys, no cloud calls.
generate_social_packGenerate one master image via Image Playground, then crop to multiple platform sizes.
generate_bundleGenerate images for a predefined bundle (e.g. "full_social", "blog_set"). Use list_bundles() to see available bundles.
generate_batchGenerate images for multiple prompts at once. Each prompt gets its own master image + optional platform crops.
add_text_overlayOverlay text on an image — for quotes, CTAs, headlines, announcements. Adds semi-transparent background behind text for readability.
add_watermarkAdd a text watermark to an image for brand protection.
create_gradientGenerate a gradient background image. Useful as a base for text posts or social media content that doesn't need a photo.
create_text_postCreate a ready-to-post text image (quote, announcement, tip). Generates a gradient or solid background with styled text. Perfect for Instagram carousel text slides or Twitter text posts.
apply_filterApply a visual filter to an image via PIL. Available: blur, sharpen, brightness, contrast, saturation, sepia, noir.
smart_cropCrop an image to exact dimensions using center-crop.
crop_imageTake an existing image and crop it to multiple platform sizes. No generation — just reformatting an image you already have.
resize_imageResize an image. Specify width/height or scale factor.
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
16/16 tools missing one or more hints — list_engines (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_presets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_bundles (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — list_engines (line 55: shortcuts_ok = subprocess.run()
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
12/16 tool handlers declare input schemas (75%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
10/16 tool handlers wrap calls in try/catch (63%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Tool description accuracy
list_engines: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/vakandi/mcp-apple-image-playground)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check