"Polymarket - A Decentralized Information Market" matching MCP servers:

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

Enables AI assistants to control a Blender instance through MCP tools, supporting scene creation, editing, and asset exchange via HTTP and background CLI processes.

An MCP server for generating images and checking generation status through ComfyUI's API. It allows interaction with local ComfyUI instances by providing workflow-based image generation and status checking tools.

Enables agents to compress JPEG, PNG, and WebP images to a target byte size, split PDFs by page or ranges, and remove image metadata while processing local files without sending file bytes over the network.

MCP server that lets AI assistants control Adobe After Effects - ExtendScript execution, background rendering, and deep project/layer inspection - with first-class Arabic/RTL and multilingual support. 44 tools.

MCP server (stdio, TypeScript) for optimising the images in a project with verified quality. Tools: analyze_images (read-only dry run) and optimize_images (in place or to a folder). Source: mcp/ in this repository; npm: optiq-mcp; MCP Registry: io.github.Baukaalm/optiq-mcp.

Compress, merge, split, OCR and convert PDFs (Word, Office, images, webpages) on local files, plus password protect and unlock, through the Papyrio API. Works without a key on a free guest tier; an optional RapidAPI key raises the limit.

Provides MCP-compatible AI agents with a verify_image tool to check a photo's capture time and provenance using C2PA, EXIF, XMP metadata, and pixel forensics, returning a verdict and confidence score.

An MCP server that searches the web for images, creates a numbered contact sheet for visual selection, and downloads the chosen images with provenance metadata. Works without an API key.

A local MCP server that provides image processing tools including resizing, cropping, format conversion, compression, rotation, flipping, thumbnailing, watermarking, effects, placeholder generation, and overlaying.

Lets a text-only LLM read images and PDFs by delegating to a vision model running on your own GPU.

Enables coding agents to turn videos from social platforms or local files into a small set of distinct frames plus a manifest, so they can answer visual questions by reading image paths. Also provides metadata lookup for captions and authors without downloading the video.

Turn a sentence into an image or a short video on your machine.

Enables users to convert video URLs into GIF images with customizable size, frame rate, time range, and looping, returning the GIF and a text summary to MCP clients.

Enables designing labels for NIIMBOT thermal printers and previewing exactly what the printhead will burn, since each design is rendered offline with NiimBlue's own code in headless Chrome and returned as a 1-bit PNG with layout warnings. It also returns an open-in-app link so the label can be reviewed and printed from NiimBlue, without the server ever touching a printer.

Enables AI agents to author node-graph-based procedural graphics as data and render them deterministically via a pinned headless engine, returning validated, hashed image artifacts with full provenance.

Enables an AI agent to capture a photo via a live camera preview, returning the image to the agent and saving it locally.

Search a YouTube video's transcript and get back only the moments that answer the question, each with a clickable timestamp deep link. Also reads the video's frames — slides, charts, demos and on-screen text — and verifies every citation against recorded evidence before returning it

Lizard Eyes — a local vision MCP server backed by Qwen3-VL-4B, exposing a single vision.inspect tool for analyzing images via llama-server.

A Model Context Protocol server that renders Apache ECharts options to SVG, enabling AI agents to generate deterministic charts server-side without a browser.