"Writing about MCP" matching MCP servers:

Generate and edit images with GPT Image 2.5 for $0.029 each, inside Claude, Cursor or any MCP client. A free you.bot API key comes with 50 credits (about 17 images) and needs no card.

Enables AI agents to analyze videos from page URLs, direct media URLs, or local files and return structured answers about visible content, speech, on-screen text, and timelines.

Enables visually lossless batch compression of JPEG, PNG, WebP, AVIF, GIF, and SVG files, writing results to a temporary preview directory with size, encoder, and quality-score details. Originals are only replaced atomically after the user confirms, with configurable effort levels and optional backups.

MCP server for AI-assisted Blender automation, providing layered tools for perception, declarative and imperative writing, and fallback operations.

MCP server for Claude Code that enables image generation and editing via Azure AI Foundry's MAI Image API, writing files to disk and returning only the path.

Enables AI agents to drive 360° cameras by connecting, checking status, reading and changing settings, taking photos, recording video, browsing the gallery, and downloading media as cancellable background jobs, with local stitching and export of 360° footage. It is honest about backend limits, returning structured, explained errors for anything a given camera or connection cannot do.

thicken turns photos of a real object into a GLB model at its real size and its metadata as JSON, read off the object by vision models and looked up in public catalogs. What it knows about each kind of object lives in a profile: a few come with thicken, and you can add your own.

An MCP server that assembles CapCut International projects by reading and writing local project files, adding captions, subtitles, overlays, and more so editors start with a mostly-done timeline. It includes tools for inspecting projects, restyling captions, importing subtitles, and rendering alpha-channel overlays via Remotion.

Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.

MCP server that captures short screen recordings as numbered, timestamped still frames and composes them into a single contact sheet returned as image content, letting AI agents reason about motion, animations, and UI transitions instead of inspecting video frame by frame. Also supports single screenshots and listing targetable windows.

Lets Claude Code or any MCP client generate images through the official Codex CLI using an existing ChatGPT plan login, with no API key or separate billing. Supports prompt-driven generation with base and reference images, writing results to a chosen path.

Converts PNG, JPEG, or WebP bitmaps into sticker-ready SVGs from any MCP client, taking local paths, HTTPS URLs, or base64 input, optionally applying a preset and writing the result to a file while returning quality metrics. It also lists available artwork presets and retrieves the result of a conversion that was still running.

Enables LLM agents to create pixel art and animations in Aseprite by writing and headlessly executing complete Lua scripts, with API documentation and output verification.

MCP server that analyzes images with Google's Gemini vision models, allowing agents to describe or ask questions about images without bloating context.

Enables coding agents to examine a rendered web page by cross-checking what the browser reports about the DOM/CSS against what is actually painted in pixels, pinpointing which element is broken and the evidence why. Reports visual problems without requiring a baseline, and is designed to grow into design-token extraction and accessibility/UX audits built on Playwright.

A read-only MCP server that lets an agent decompile Final Cut Pro FCPXML timelines into compact briefs, resolve multicam angles, compounds and retimes exactly, and run safety checks for transition handles, jump-cut dissolves, missing effects, relink problems and timeline diffs. It also supports applying edits from an annotated brief and guarded, plan-and-ledger-checked imports into a named library, always writing to new files and reporting anything unverifiable as REVIEW rather than passing.

Exposes information about Z-Image AI image generation and editing platform, including styles, pricing, and official links, for MCP-compatible AI clients.

Enables reading and patching VRoid Studio 2.x .vroid files by inspecting textures and parameters, exporting layer PNGs, and writing verified new files with replaced layers, item colors, or saved settings.

Provides access to AI Swap Face's image generation styles, pricing, FAQ, and official links. Enables AI clients to retrieve information about this online face-swapping tool.

About MCP server for image conversion, resizing, and merging — runs locally, no uploads

Enables AI agents to browse and manage a gThumb image library by reading and writing catalogs, tags, ratings, comments, thumbnails, and search results directly in gThumb’s own data.

A universal vision MCP server that enables Claude Code and Claude Desktop to describe images, extract text, and answer questions about images by converting visual content to text via multiple AI providers.

Enables any MCP-compatible AI agent to directly operate PixInsight through about 80 tools for opening and editing images, running processes, PixelMath, astrometry, and channel operations.

Enables reading, writing, drawing, and animating .aseprite pixel art and sprites natively in pure Python, including converting images to true pixel art, rigging and tweening characters, linting and comparing frames, and exporting GIFs or sprite sheets. It runs fast without launching Aseprite, keeps edits transactional with undo/redo, and includes a built-in web viewer for playback and review.

Enables high-quality 3D-style cartoon image generation using Google Gemini AI alongside secure file system operations like reading, writing, and managing directories. It provides a dual-purpose toolkit for creative asset generation and local file management via the Model Context Protocol.

Enables AI assistants to turn a story into a finished PS1-style low-poly 3D vertical short video by writing the script, voicing lines with ElevenLabs, building the three.js scene from a prop library, and rendering seamless looping takes with mixed audio, stills, QC and a posting kit.

Enables Claude Code and Gemini CLI to see your macOS screen, answering questions about the file, error, UI, database table, or web page you're looking at. Captures screenshots, reads database schemas, and controls Chrome/Brave, presenting answers as on-screen highlights or spoken bubbles above your cursor.

Enables AI agents to query real-time spatial perception from DePIN edge-vision nodes, retrieving structured JSON about detected objects, bounding boxes, confidence scores, environmental state, and geolocation through the Model Context Protocol.

Enables AI assistants to capture and analyze screenshots using Claude Vision API, providing AI-powered insights about desktop interface content, UI elements, and visual layouts.

Enables users to capture current lab-camera views, ask a cloud VLM questions about them, save JPEG snapshots, optionally control PTZ, and access Opentrons device tools through MCP.

Enables AI agents to drive Adobe Lightroom Classic directly — searching and organizing catalogs, reading and writing the full set of develop parameters, building geometric and AI-generated masks (sky, subject, mountains, water, people), applying presets, and rendering previews, histograms, and exports. All capabilities are exposed as 167 MCP tools over a Lua plugin bridge, with write-confirmation sentinels so silently dropped edits surface as explicit errors.

Enables AI coding agents to perform end-to-end medical image analysis locally, from inspecting CT/MRI/X-ray studies and running containerized segmentation models like MedSAM2, TotalSegmentator, and HD-BET to refining masks, measuring volumes, and writing reports. It pairs preset or custom guideline protocols with a code-customizable viewer that renders images back to agents as annotated PNGs and to humans as interactive HTML.

Enables AI agents to cull photo shoots by evaluating sharpness, eye-openness, and aesthetics, and writing reversible XMP sidecars for Lightroom, with strict safety gates to prevent unauthorized writes.

An MCP connector that lets Claude create and edit pixel-art sprites by writing rows of character keys and drawing commands, organized into projects with palettes, swaps, animation and export. Every save returns zoomed previews, real-size copies, silhouettes and automatic checks, and the same sprites can be viewed and painted by hand in a browser.

Enables an AI assistant to upload local images and videos to a memory service and later ask natural-language questions about everything stored. Runs locally over stdio and returns answers with their sources.

Enables AI agents to drive a live Blender session over stdio, inspecting the scene graph, searching and calling operators, reading and writing RNA properties, rendering viewable images, and checkpointing or restoring the file across a multi-turn conversation. It also exposes gallery and scene-reset helpers so the agent can check its own work and start over cleanly.

Lets agents watch public YouTube videos and answer questions about their audio and visuals, using Gemini for transcript-aware or fixed-frame analysis.

Enables text-only LLMs to ask questions about local image files or image URLs using Google AI Studio's free Gemma tier, including comparing multiple images in a single request.

Generates images from English scene descriptions using OpenAI's gpt-image-2 (with optional xAI fallback), including automatic safe retry on content rejection, monochrome border trimming, and prompt-writing guidance.

Enables AI agents to analyze and interact with Android phone screens via ADB, using the AutoGLM model to answer queries about screen content and coordinates.