add_border
Add a solid color border around an image.
Free tool — runs locally, no account needed.
LABSCO SUMMARY
Free where the work can be local, paid only where it has to reach a GPU.
The tiering is stated plainly and it decides the cost: resizing, cropping, watermarking and format conversion run on your machine for nothing, background removal and upscaling get three free runs a day, and only the generation work — product shots, avatars, prompt edits, video — draws credits, at rates the tool descriptions state up front. In practice that means an agent can do the entire dull half of image work before an account exists.
What it is
Image tooling in three tiers: local edits that run offline with no account, AI tools with a small free daily allowance, and paid generation — product photos, try-on, scenes, avatars, video — that needs a PixelPanda token and spends credits.
What you get
- Local edits with no account and no network: resize, crop, rotate, flip, grayscale, invert, rounded corners, borders, compression, and conversion between PNG, JPEG, WebP, BMP and TIFF
- Several images merged horizontally, vertically or as a grid, with a gap between them
- Opacity, Gaussian blur, pixelation, text watermarks placed centred, cornered or tiled, and brightness, contrast, sharpness and saturation adjusted
- A profile picture cut as a circle, square or rounded square at the size you name
- An image's dimensions, format, file size, colour mode and DPI
- AI background removal to a transparent PNG, 2x or 4x upscaling with Real-ESRGAN, text and watermark removal by OCR and inpainting, and image analysis for objects, colours, composition, quality and mood — free for 3 uses a day without an account
- Product photography: a product uploaded, then product photos with an avatar, try-on shots, or lifestyle, studio and detail scenes with no avatar at all
- Reusable AI avatars generated, either guided or matched to the look of a reference photo
- An image reverse-engineered into four ready-to-use prompt variants — general, Flux, Midjourney v6 and Stable Diffusion
- Text-prompt image editing through FLUX.1 Kontext Pro, keeping the subject while colours, scenes or elements change
- A UGC-style video animated from a still, with native audio and lip-sync generated from a script
- Six enhancement variants from one image — AI Restore, Vivid Restore, Conservative, Face Restore, Face Enhance and GFPGAN Restore
- Job, avatar and video generations polled to completion, recent jobs listed, and the credit balance checked
Requirements
uvx pixelpanda-mcp, or pip install pixelpanda-mcp. The token is optional: every local tool and the free AI tier work without one, and PIXELPANDA_API_TOKEN — a pk_live_ key — is needed only for the paid tools. The free AI tools are capped at 3 uses a day without an account. Credits are what the paid tools spend: 1 per generated product photo, try-on shot, scene, avatar or image-to-prompt run, 2 for a prompt-driven edit, and 50 for a video. PIXELPANDA_API_URL overrides the API base, which defaults to https://pixelpanda.ai.
Setup effort
One command — uvx pixelpanda-mcp
USE CASES
01
Getting a screenshot ready to send
Crop it, resize it and compress it to WebP, with nothing leaving the machine.
02
Cutting a product out of its background
Remove the background to a transparent PNG, then upscale it if it came out too small.
03
Making a profile picture out of a photo
Adjust brightness and sharpness first, then cut it to a circle at the size you need.
04
Putting a product in a shot you never took
Upload the product, pick one of your avatars, and generate the product photos or try-on images.
05
Getting listing images without a studio
Generate lifestyle, studio and detail scenes from the product alone, with no avatar involved.
06
Reproducing a look you liked
Reverse-engineer the image into prompt variants aimed at Flux, Midjourney or Stable Diffusion.
07
Changing one thing in an image
Edit it from a text prompt so the colour or the scene changes while the subject stays put.
08
Tidying up a batch of screenshots
Merge them into a grid, add the watermark, and check the dimensions of what came out.
38 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
add_watermark
Add a text watermark to an image. Position: center, bottom-right, or tiled.
Free tool — runs locally, no account needed.
adjust_image
Adjust brightness, contrast, sharpness, and saturation. 1.0 = no change, >1 = increase, <1 = decrease.
Free tool — runs locally, no account needed.
analyze_image
Analyze an image with AI — detect objects, colors, text, composition, quality, and mood.
Free tool — 3 uses/day without an account. Unlimited with a PixelPanda API token.
blur_image
Apply Gaussian blur to an image.
Free tool — runs locally, no account needed.
check_avatar_status
Check an avatar generation job started with generate_avatar.
Requires PIXELPANDA_API_TOKEN.
check_credits
Check your PixelPanda credit balance and account info.
Requires PIXELPANDA_API_TOKEN.
check_job_status
Check the status of an AI generation job. Returns progress and result URLs when complete.
Requires PIXELPANDA_API_TOKEN.
check_video_status
Check a video generation job started with generate_video.
Requires PIXELPANDA_API_TOKEN.
compress_image
Compress an image by reducing quality. Output format: jpeg, webp, or png.
Free tool — runs locally, no account needed.
convert_format
Convert an image to a different format: png, jpeg, webp, bmp, tiff.
Free tool — runs locally, no account needed.
create_profile_picture
Create a profile picture from an image. Shape: circle, square, or rounded.
Free tool — runs locally, no account needed.
crop_image
Crop an image to the specified rectangle (left, top, right, bottom in pixels).
Free tool — runs locally, no account needed.
edit_image
Edit an image with a text prompt — AI image-to-image (2 credits).
FLUX.1 Kontext Pro: change colors, swap scenes, restyle, add or remove elements while keeping the subject intact.
strength: 0.0-0.3 subtle, 0.4-0.6 moderate, 0.7-1.0 strong. Requires PIXELPANDA_API_TOKEN. Provide either file_path or image_url.
enhance_image
Enhance, sharpen, and restore an image using multiple AI methods.
Returns 6 variants (AI Restore, Vivid Restore, Conservative, Face Restore, Face Enhance, GFPGAN Restore). Cost: 1 credit. Provide either image_url (public URL) or file_path (local file).
Requires PIXELPANDA_API_TOKEN.
flip_image
Flip an image horizontally or vertically.
Free tool — runs locally, no account needed.
generate_avatar
Generate AI avatars — reusable characters for product photos, try-on, and video (1 credit each).
Pass reference_image_url to match the look of an existing photo, otherwise the avatar is built from prompt. Returns a job id; poll with check_avatar_status.
Requires PIXELPANDA_API_TOKEN.
generate_product_photo
Generate AI product photos with an avatar holding/using your product. 1 credit per image.
Requires PIXELPANDA_API_TOKEN. Use list_avatars and list_products to get UUIDs.
generate_scenes
Generate AI product scene photos (lifestyle, studio, detail shots). No avatar needed. 1 credit per scene.
Requires PIXELPANDA_API_TOKEN.
generate_tryon
Generate AI try-on photos with an avatar wearing your product (clothing). 1 credit per image.
Requires PIXELPANDA_API_TOKEN.
generate_video
Generate a UGC-style video from a still image (50 credits).
Animates the image with xAI Grok Imagine, which produces native audio and lip-sync directly from script — no separate voiceover step. Returns a job id; poll with check_video_status. Takes a few minutes.
Note: video can only animate what is already in the source image — it cannot add a product that isn't pictured.
Requires PIXELPANDA_API_TOKEN. Duration: 5, 8, or 10 seconds.
get_image_info
Get detailed information about an image: dimensions, format, file size, color mode, DPI.
Free tool — runs locally, no account needed.
grayscale_image
Convert an image to grayscale.
Free tool — runs locally, no account needed.
image_to_prompt
Reverse-engineer an image into ready-to-use AI-art prompts (1 credit).
Returns four prompt variants tuned for different generators: general, Flux, Midjourney v6, and Stable Diffusion (positive + negative). Useful for recreating a style or generating variations of a reference.
Requires PIXELPANDA_API_TOKEN. Provide either file_path or image_url.
invert_image
Invert the colors of an image (negative).
Free tool — runs locally, no account needed.
list_avatars
List your saved AI avatars (for use in product photo generation).
Requires PIXELPANDA_API_TOKEN.
list_jobs
List your recent AI generation jobs.
Requires PIXELPANDA_API_TOKEN.
list_products
List your saved products in PixelPanda.
Requires PIXELPANDA_API_TOKEN.
make_transparent
Adjust the opacity/transparency of an image. 0.0 = fully transparent, 1.0 = fully opaque.
Free tool — runs locally, no account needed.
merge_images
Merge multiple images into one. Direction: horizontal, vertical, or grid.
Free tool — runs locally, no account needed.
pixelate_image
Pixelate an image with a given pixel block size.
Free tool — runs locally, no account needed.
remove_background
Remove the background from an image using AI. Returns a transparent PNG.
Free tool — 3 uses/day without an account. Unlimited with a PixelPanda API token.
remove_text
Remove text and watermarks from an image using AI (OCR + inpainting).
Free tool — 3 uses/day without an account. Unlimited with a PixelPanda API token.
resize_image
Resize an image. Specify width, height, or both. Maintains aspect ratio by default.
Free tool — runs locally, no account needed.
rotate_image
Rotate an image by the specified degrees (counter-clockwise). Expands canvas by default.
Free tool — runs locally, no account needed.
round_corners
Round the corners of an image with a specified radius.
Free tool — runs locally, no account needed.
upload_product
Upload a product image to PixelPanda for use in AI photo generation.
Requires PIXELPANDA_API_TOKEN. Categories: clothing, accessories, shoes, bags, jewelry, electronics, food, beauty, home, other.
upscale_image
Upscale an image 2x or 4x using AI (Real-ESRGAN). Enhances resolution and sharpness.
Free tool — 3 uses/day without an account. Unlimited with a PixelPanda API token.
BEFORE YOU INSTALL
What to know first
Tools you get
38 tools when we connected. 18 local tools work offline, 4 AI tools are free at 3 uses a day, and 15 Pro tools need PIXELPANDA_API_TOKEN and credits; generate_video costs 50. enhance_image is missing from the documentation.
Requires
uvx on PATH
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Moderate Standing cost
Rated by the size of the 38 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx pixelpanda-mcpMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"pixelpanda": {
"command": "uvx",
"args": [
"pixelpanda-mcp"
],
"env": {
"PIXELPANDA_API_TOKEN": "<YOUR_PIXELPANDA_API_TOKEN>"
}
}
}
}
