"Browser Automation" matching MCP servers:

Extracts text from images and browser screenshots locally using Tesseract.js, without sending image data to the LLM.

Windows desktop automation MCP server enabling screenshot capture, precise visual locating of UI elements via vision models, and automated mouse clicking.

Controls Google Flow for image and video generation from an AI agent. Enables generating images with models like Imagen 4, creating videos, managing characters and scenes via browser automation.

Provides image recognition capabilities to Codex/Claude Code by routing 'look at screen/screenshot' requests to a multimodal model via an API relay. Enables UI automation agents to analyze local screenshots and return descriptions or structured JSON coordinates.

Enables image generation and editing through the Gemini web app using your own browser session cookies, avoiding API keys and per-image billing.

Author, validate, preview, and render motion-graphics videos from a single JSON document (Clipkit Protocol). 16 tools with in-chat PNG previews, captions, templated promos, and hand-off to a free browser editor by link.

FableCut is a Premiere-style non-linear video editor that runs entirely in your browser — and exposes its whole timeline as one JSON document. Edit it by hand, from the UI, or let an AI agent (Claude Code, Claude Desktop, or anything that speaks MCP/REST) cut your video for you while you watch the timeline update live.

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

Enables Claude to generate and edit images through a live-discovered model catalog, including masked edits and exact output sizes, with browser-based sign-in and cost-annotated saved results. It runs locally over stdio and stores images in a configurable directory.

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

MCP server for Google Gemini that enables image generation, editing, file analysis, and chat using browser cookies, no API key needed.

Lets agents directly read and edit the live ComfyUI canvas in a browser while retaining official Comfy MCP headless tools and local management.

MCP server that analyzes videos locally with frame-by-frame understanding and optional browser sidecars, producing structured context bundles for coding agents to fix bugs, add features, or build new functionality.

Gemini MCP with image, video, svg, landing page generation and search. Grounded search, deep research, image generation... Having them as tools inside Claude beats switching between browser tabs.

Local multimodal MCP server for vision, document, audio, video, and GUI automation, all processed locally on Apple Silicon for privacy and security.

Enables AI agents to perform advanced image editing and graphic design through Photopea, a browser-based Photoshop alternative. Provides 34 tools for document management, layer operations, filters, adjustments, and exports via a WebSocket bridge to the browser.

Enables agents to search starter-track metadata, retrieve original scene templates, and prepare editable playlist-video drafts with optional captions and a browser workspace URL.

Enables AI agents to command browser-based AI generation models (like Imagen 3, Omni Flash, Veo 3) through the Autoflow Chrome Extension, with background queueing for autonomous media generation.

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 headless-first Model Context Protocol server for safe, deterministic Blender automation, exposing typed tools to inspect scenes and render previews without arbitrary command execution.