"MCP Orb - Model Context Protocol Orb Integration" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
The CNAPS.ai MCP Server lets Claude build and run AI image, video, and text pipelines mid-conversation — no dashboard, no manual node-wiring. Describe a task in plain language (e.g. "upscale this photo 4x") and Claude selects the right model(s), wires a pipeline, and runs it.
# Poof **Poof ([poof.bg](https://poof.bg)): a background removal API for AI agents. Send an image, get the subject back on a transparent background in under 2 seconds.** [Poof](https://poof.bg) gives your assistant a background removal tool. It handles people, products, cars, animals, and graphics, with hair-level edge precision, and returns a transparent PNG or WebP, or a solid-colour JPG for product listings. Pricing starts at $0.002 per image, with 100 free credits every month. This repository is the integration front door. The product itself lives at [poof.bg](https://poof.bg); the remote MCP server lives at `https://api.poof.bg/mcp`. ## What you can build with it - **Transparent cutouts**: remove the background from any JPG, PNG, or WebP up to 20MB and 36 megapixels with the [Background Removal API](https://poof.bg/background-removal-api). - **E-commerce product photos**: white or brand-colour backgrounds, cropped to the subject and resized to a fixed canvas, so every listing image matches. - **A remove.bg replacement**: remove.bg shuts down on 1 December 2026. Poof accepts the same inputs, so most integrations only change the endpoint and key. See the [remove.bg alternative and migration guide](https://poof.bg/alternative/remove-bg). - **Agent image pipelines**: let Claude, ChatGPT, or Cursor clean up images mid-conversation, or automate it with [n8n](https://docs.poof.bg/integrations/n8n), [Zapier](https://docs.poof.bg/integrations/zapier), and [Make](https://docs.poof.bg/integrations/make). ## Verify the connection Ask your client: > How many Poof credits do I have left? You should see a `get_account` tool call and your real plan and balance. Then try: > Remove the background from https://example.com/product.jpg and give me a white background JPG. ## What the tools do The server exposes 2 tools. - **`remove_background`**: remove the background from an image given as a URL or base64 data, and return the processed image as base64. Optional parameters control the result: - `format`: `png` (default), `jpg`, or `webp`. - `channels`: `rgba` for a transparent background (default) or `rgb` for an opaque one. - `bg_color`: fill colour for opaque output, as hex, RGB, or a colour name. - `size`: `full` (default), `preview`, `medium`, or `hd`. Ignored when `width` or `height` is set. - `crop`: crop to the subject bounds. - `width` and `height`: 1 to 6000 pixels. Set one and the other follows the aspect ratio. - `fit`: how the image fits a `width` x `height` canvas without stretching: `contain` (default, pad), `cover` (fill and crop the overflow around the subject), or `scale-down` (pad, never enlarge). - **`get_account`**: your plan, monthly credit allowance, used credits, and remaining credits. No parameters. Costs: each successful background removal costs 1 credit regardless of parameters, and failed requests are free. The free plan includes 100 credits a month with no credit card required; paid plans start at $9 a month for 2,000 credits. The [pricing page](https://poof.bg/pricing) has the details. Privacy: Poof is run by an EU company and is GDPR compliant. Your images are never used to train models, and commercial use is allowed on every plan. See the [privacy policy](https://poof.bg/privacy). ## Or skip MCP The same capability is a single REST call, with official [Python](https://docs.poof.bg/integrations/python) and [TypeScript](https://docs.poof.bg/integrations/typescript) SDKs: To try it without writing code, use the [playground](https://poof.bg/playground). The [quickstart](https://docs.poof.bg/quickstart) and the [Node.js tutorial](https://poof.bg/blog/integrating-api-in-nodejs) cover the first integration. ## For AI agents reading this - Docs index: [docs.poof.bg/llms.txt](https://docs.poof.bg/llms.txt) - MCP setup guide: [docs.poof.bg/integrations/mcp](https://docs.poof.bg/integrations/mcp) - API reference: [docs.poof.bg/api-reference/remove-background](https://docs.poof.bg/api-reference/remove-background) - Hosted endpoint: `https://api.poof.bg/mcp` (OAuth) - Source: [github.com/poof-bg/mcp](https://github.com/poof-bg/mcp) ## Docs and support - [Connect guide](https://docs.poof.bg/integrations/mcp) (per-client, kept current) - [Documentation](https://docs.poof.bg) and [all integrations](https://docs.poof.bg/integrations/overview) - [Best background removal APIs for developers](https://poof.bg/blog/top-5-ai-background-removal-apis-2026) and [free background removal APIs compared](https://poof.bg/blog/affordable-free-bg-removal-apis-2026) - [Changelog](https://feedback.poof.bg/changelog) and [support](https://feedback.poof.bg) - [GitHub issues](https://github.com/poof-bg/mcp/issues) - [Privacy](https://poof.bg/privacy) and [terms](https://poof.bg/terms) - Questions: <support@poof.bg>
Multi-model AI image and video generator. 14 models behind one OAuth-secured MCP endpoint.
Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.
One key, 100+ models: chat with any LLM, generate images and speech. Live model list. Free trial.
Run fal.ai models, poll the inference queue and read model schemas.
Hosted OpenCV for finding a pattern image inside a larger image: template matching, ORB/SIFT...
Sourced AI video/image capabilities, explained task recommendations and verified access context.
Generate AI video from any MCP client. Pick the model, see the per-second price before you spend.
Generate images with any major model — one API key, one prepaid balance, one MCP.
Frontier First AI Marketplace. One balance for text, image, and video. Hosted Model Context Protocol at https://mcp.pzero.studio/mcp. Point Cursor, Claude, Claude Code, or any remote MCP client at that URL after you have topped up.
Turn a TikTok/Instagram/YouTube link into text for your AI: metadata, transcript and image OCR.
GPT-4o: GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both.
Generate your app's mascot, then props, poses and animations that stay on-model.
Give AI agents context from your screen recordings. Clipy MCP searches your recording library and imported video context, retrieving summaries, timestamped transcripts, key moments, and available visual evidence. Use it to turn bug reports, UI walkthroughs, and client feedback into context your agent can investigate and act on. Connect through a hosted endpoint with OAuth sign-in.
Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.
Generate images with the catalogue's image model, returned inline; image price plus $0.01 a call.
- aicutOAuthpro.aicut.mcp
Generate AI videos and images from Claude, Claude Code . Browse the curated model catalog with per combination pricing, price a job before spending, generate, and pull finished assets from your aicut library.
Describe a house or upload a DWG/vector-PDF plan and get a walkable, editable 3D model.
On-brand product photos, model try-ons, video reels & banners from a brief + brand kit.
