Compute perceptual hashes (aHash, dHash, pHash, wHash) of an image. Optionally compare two images using Hamming distance to detect near-duplicates.
MIT
730,286 tools. Updated 2026-10-31 19:48
"Generating a series of images using MCP from a sample image" matching MCP tools:
- For a user's image request, load the `generating-images` skill BEFORE calling this — it picks the right model and builds the prompt (this tool does neither, and calling it raw gives weak, inconsistent results).Apache 2.0
- Replace the background of an input image with a new scene described by a text prompt, using customizable visual styles.MIT
- Preview a sample of records from a table, with optional column selection and filtering, to understand its structure and content.Apache 2.0
- Transform an input image into a new image guided by a text prompt, adjusting the influence of the original image with a strength parameter.MIT
- Generate images from text prompts, optionally with reference images for editing. Returns finished image URLs and previews.MIT
Matching MCP Servers
- AlicenseAqualityDmaintenanceMCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.11MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.1MIT
Matching MCP Connectors
Search institutional series-a venture capital firms, partner profiles, and valuation.
Indicative UK skip hire prices by town, council skip permit rules and skip size recommendations.
- Create an image from a text prompt with selectable aspect ratios. Renders photorealistic scenes, illustrations, and readable in-image text.MIT
- Create images from text descriptions. Choose size, style, model, and number of images to generate.MIT
- Retrieve a curated list of featured AI workflows for generating images, text, and other content.MIT
- Create or edit images from a text prompt, using reference image URLs for edits and variations. Returns a hosted image URL for download or reuse.MITDestructive
- Remove unwanted objects from a photo using a mask image. Returns the cleaned image URL, or saves it to a Pedra property gallery when a propertyId is provided.MIT
- Create a visual style from up to five reference images and return its ID for use in image generation.MIT
- Extracts numerical data from line and scatter plot images. Converts visual series into precise data points for further analysis.MIT
- Extract a color palette from images on any public URL to generate design tokens, theme components, or check accessibility contrast.MIT
- Generate high-resolution images, diagrams, and UI assets from text prompts using Gemini 3 Pro Image or Gemini 2.5 Flash Image.MIT
- Generate images from visual prompts through the NormaHub API using GPT Image or Grok Imagine models.MIT
- Generate images from text prompts using OpenAI models. Choose from multiple output formats and settings to get custom images.MIT
- Generate images from text descriptions using Pollinations models. Supports optional reference images for image-to-image generation.Apache 2.0
- Generate 2 to 15 coherent image variations from a prompt or base image for A/B testing, storyboards, product variations, and social media content.MIT
- Generate images from text prompts using any OpenRouter image model. Saves files and returns paths, model, and cost.Apache 2.0
- Extract markdown text from a publicly accessible PDF or image URL, and optionally save the output and images to disk.MIT