"browser use" matching MCP servers:

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

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.

Local MCP server for Gateway-managed computer use that exposes computer.* tools with desktop control, OCR, and user-visible safety overlays.

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

Use APIKO image and video models from Claude Code and Codex with your own API key: look up models and request fields, quote a list price, generate images and videos, follow tasks and upload reference images.

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.

MCP server that allows AI coding agents to search, download, and convert stock photos from Pexels, Unsplash, and Pixabay into WebP format for direct use in web development projects.

Enables precise extraction of PDF content, including text coordinates, vector shapes, images, and on-demand raster rendering, for use cases like reconstructing design files.

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.

A lightweight Node.js MCP server that integrates Alibaba Cloud's Qwen models, providing vision understanding, real-time web search, and general chat capabilities through three ready-to-use tools.

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.

A standalone MCP server (also usable as a Node library) that lets an AI host browse its QQ favorite-sticker knowledge base, search web meme libraries by emotion keywords, preview images before use, record what each sticker means, and send a single sticker into whitelisted QQ groups or private chats. It enforces whitelists, per-session cooldowns and hourly caps, human-like send pauses, SSRF-safe image downloading, and prompt-injection-resistant sticker notes.

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.

Enables AI coding agents to search pins, inspect and preview images, find related pins, read public boards, and download full-resolution originals with no login, API key, or headless browser required.

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.

An MCP server that searches booru image boards and cleans their tags into ready-to-use AI-art prompts for Stable Diffusion and similar models.

A local MCP server that integrates Step Plan API for image generation and text-to-speech, allowing MCP-compatible clients like Codex to use these capabilities without switching models.

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.