"Deep research on Gemini" matching MCP servers:

Enables AI agents to compose fake chat conversations and generate deep links to a pre-filled mock screenshot generator for parody, education, and design mockups.

MCP server that gives LLMs deep knowledge of design systems and tokens, enabling intelligent design evolution, token analysis, and designer-to-developer handoffs.

Enables multimodal AI to convert photos with reference objects into parametric OpenSCAD models and watertight 3D-printable STL files, including calibration, part generation, and printability inspection.

MCP server for UI research that helps agents discover visual patterns, generate original HTML/CSS components, and track deliverables without copying third-party code.

An MCP server that provides access to Google Gemini models via Vertex AI, enabling text generation, multi-turn chat, image/video generation, and frontend design through Claude Code.

Enables vision-capable AI clients to read and adjust Capture One on macOS through local MCP stdio or JSON CLI, including curves, color tools, film grain, masks, reference matching, and real previews of rendered edits.

Enables safe, observable Blender research by exposing structured tools for viewport capture, object and material edits, semantic scene creation, and managed .blend project lifecycles with transactional rollback and validation.

Enables vision-capable AI clients to read and adjust Capture One on Windows through an MCP stdio server (plus a JSON CLI), applying exposure, curves, color, layer and mask edits and returning real Capture One-rendered previews. It runs a local bridge to C1's native parameters with no presets, screenshots or synthetic input.

Enables MCP clients to create and edit technical drawings, manage layers and geometry, process GIS/research mapping data, generate previews and layouts, and automate AutoCAD documents on Windows through COM.

Unofficial MCP server for appshots.design that enables AI assistants to search and view real app screenshots for grounded design research.

Enables integrating Figma with AI assistants like Claude Desktop and Gemini CLI for accessing and managing Figma design files.

An MCP server that provides AI tools with deep understanding of WireUI v2.x components and comprehensive icon support for Heroicons and Phosphor Icons.

Provides AI-powered UI design, repo intelligence, and frontend code generation tools, enabling assistants to scaffold projects, generate and modify UI components, manage design tokens, and analyze repositories.

Enables retrieval of structured architectural case study data for design research, supporting case browsing, filtering, and downloadable research packages through natural language.

Provides AI-powered tools for UX/UI review, web component generation, and code refactoring using Google Gemini.

Generates frontend UI code from text descriptions, screenshots, or iterative refinement using Gemini 2.5 Flash.

Compose fake chat conversations and receive deep links to a pre-filled generator for preview, parody, and design mockups.

Enables AI agents to manage routes on the Design Canvas infinite canvas app, including adding, removing, listing routes, and capturing screenshots of the canvas.

Manages design tokens (colors, spacing, fonts) in a JSON file and enables agents to read, write, export, and detect drift between tokens and CSS via MCP.

Enables inspecting, creating and modifying MakeHuman characters inside Blender — phenotypes, rigs, assets, skins, faces, expressions and saved presets — through 34 named tools served by a companion Blender bridge add-on that dispatches a closed command vocabulary instead of executing code. It also exposes read-only introspection, catalogue and documentation lookups that always answer, even when Blender is unreachable.

Exposes surface-bound annotations placed on a Blender model to AI agents, letting them read pending change requests with stable IDs, revisions, positions and visibility, then submit completion summaries by marker ID after editing. This enables batch, review-oriented workflows where the user approves or rejects each agent change in Blender, without requiring object selection, screenshots, or a fixed port bridge.

Give your AI assistant the ability to inspect, measure, and compare 3D CAD models by dropping in a STEP file and asking engineering questions. Runs entirely on your machine with no cloud, no CAD license, and no setup.

Enables an AI assistant to conversationally control Autodesk AutoCAD, drawing, inspecting, and editing plans, and includes a cross-platform DXF engine that runs without AutoCAD on macOS and Linux. It exposes tools for rendering views as images, batching geometry, blocks, and structures, measuring and checking plans, and undoing whole batches.

Enables AI agents to read and draw on Figma canvas safely, with built-in safeguards for layout, overlays, and verification.

Bidirectional MCP bridge enabling AI assistants to draw UI on Figma canvas and read designs back as structured data or code tokens via localhost, requiring Figma Desktop.

MCP server that gives AI agents browser-based access to Mobbin for design research, screen discovery, and screenshot collection through automated browser control.

A visual designer pen for Claude Code that lets users click, drag, or draw on webpages to get source code locations and screenshots for direct editing and verification.

Enables coding agents to read ground truth about a React design system — components, props, cva variants, tokens and docs — over MCP so they write UI that matches it. It also exposes a check_ui linter agents run on their own output, returning rule ids, locations and concrete fixes before review.

Enables MCP clients to read design structure, take screenshots, create nodes, and edit UI directly on Figma canvas via a bridge between MCP and Figma Desktop.

Lets Claude Code, Cursor, VS Code and other AI agents draw and edit draw.io diagrams from your project's files, on a live browser canvas you can also edit by hand. Includes version history, undo, cloud shape libraries (AWS, Azure, GCP) and PNG or SVG export.