"A more powerful and accurate web search agent for use with Cursor" matching MCP servers:

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

A self-hosted MCP server that enables AI agents to see and control a Windows PC through screenshots, built-in Arabic/English OCR, mouse, keyboard, clipboard, and application launching, with code-enforced consent and audit logging.

Enables ChatGPT users to search and browse a private photo library, inspect metadata, and receive real image previews through read-only tools, while keeping encrypted sessions server-side.

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.

Enables AI assistants like Claude, Cursor, and VS Code to generate Grok Imagine images and videos through the user's existing logged-in grok.com browser session, with no xAI API key required. Supports aspect ratio and size control, batch prompts, and daily quota limits.

Enables AI-driven 3D modeling and scene creation in Blender, allowing LLMs to create, modify, and manipulate objects, materials, and assets through natural language.

A streamlined MCP server for XMP metadata embedding with beautiful formatting and smart filename indicators, enabling metadata embedding, reading, validation, and report generation for lifestyle, product, and orbit schemas.

Unofficial MCP server for generating images via Midjourney web app using authentication cookies. Enables text-to-image generation with customizable parameters.

Enables MCP clients to discover OpenRouter image and video models, generate and edit images, create variations, launch and monitor video jobs, and save resulting media into authorized local project directories with cost controls.

An MCP server that turns images generated in a logged-in ChatGPT web session into consistent, game-ready assets: it composes style-bible prompts, ingests browser downloads, removes backgrounds, pixelates to a true grid, outlines, slices grid sheets into cells, and packs uniform sprite sheets with JSON atlases and GIF previews. Everything runs locally in pure JavaScript with no API key or native dependencies.

A customizable Model Context Protocol server implementation that enables AI models to interact with external tools including weather queries, Google search, and camera control functionality.

Generates all required web app icons and manifest files from a single source image with framework auto-detection. Supports Next.js App Router, traditional web apps, and PWA standards with zero configuration.

Enables local agents to send conversations and image-generation requests through user-authorized web chat and Flow Chrome tabs, poll or cancel jobs, and download generated images without API keys or remote debugging. Runs locally over stdio with explicit per-request confirmation and token-paired extension controls.

Connects an AI assistant directly to a Doubao web account so it can hold conversations, generate images from text, and turn images into videos, saving outputs to disk automatically. Includes multi-account pooling with hot-swapping for quota or risk-control limits, and requires no local service, API key, or external dependency at runtime.

Enables local image generation through a ChatGPT web account, downloading original files with paths, sizes, and checksums while keeping responses compact. Supports batched requests and resumable recovery without embedding images in model context.

Hosted MCP server (OAuth, no API keys) that makes short drama series (micro-dramas, sitcoms, K-drama style, any language) and other short vertical videos from Claude, ChatGPT or Codex, with the same cast every episode.

Enables users to generate, edit, and iteratively refine images through a logged-in ChatGPT web session, while managing image libraries, style presets, character profiles, and background jobs.

Privacy-first MCP server for macOS that allows AI agents to search local images using natural language descriptions, leveraging MLX CLIP embeddings and LanceDB for fast, fully offline search.

Enables natural language search of local photo archives using AI-powered semantic understanding, with integration into Claude Desktop via the Model Context Protocol.

Enables non-vision LLMs to analyze images via any OpenAI-compatible vision API. Hardened against truncation, empty responses, and timeouts for reliable analysis.

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 lightweight MCP server that enables text agents to analyze images and videos using OpenAI-compatible vision models, with tools for image analysis and video frame extraction.

Provides a catalog of paid micro-work tools for text processing, speech, and image generation with fixed USDC pricing via x402. Enables agents to discover capabilities, get quotes, and prepare calls without handling wallet keys.

Provides vision capabilities to Reasonix, enabling analysis of images/videos, OCR, and comparisons via OpenAI-compatible vision models.

Bridges DeepSeek (text-only) with vision models via MCP, enabling image description and compression using any OpenAI-compatible visual API.

A local stdio MCP server for visual AI work, offering an Excalidraw infinite canvas, image generation and editing, HTML drafts, presentations, and durable task recovery within a project workspace.

Enables AI agents to search, retrieve, store, move, render, measure, and de-identify DICOM images across DIMSE and DICOMweb archives with one set of tools, including local pixel and geometry analysis.

Enables MCP clients such as Claude Code, Codex, or Pi to search for existing images through ZCode's search_image interface using required query, count, gl, and rank parameters. It does not generate images.

MCP server for searching images with Google

Enables AI assistants to programmatically inspect projects, create compositions and layers, apply effects, animate properties, and manage render jobs in Adobe After Effects through natural language.