"Archive of Our Own" matching MCP servers:

Enables AI agents to create and configure product mockups on ultramock.io using your own logged-in subscription.

Drives the real Claude Design web app from your editor or agent, enabling creation, iteration, and retrieval of designs generated on your own claude.ai account via automated browser interaction.

A multi-user remote MCP server exposing 413 Autodesk Construction Cloud / Forma API tools with per-user Autodesk sign-in, enabling management of issues, RFIs, submittals, sheets, and more while each user only sees their own data.

Enables design agents to freeze their own prediction of an audience's tastes, measure that audience with Qloo, and then bind palettes, type, motion, illustration and voice to what the prediction missed. It validates the resulting design decisions against the project's own design system, captures screenshots, and produces a provenance report showing where each choice came from.

Enables a coding agent to create, read, write and link HTML-native artboards, capture screenshots of its own rendered output, and collect queued canvas feedback so it can see and refine UI designs in a loop. Provides tools such as screenshot_artboard, write_artboard and get_pending_marks to close the write-render-look-fix cycle on real HTML files.

Enables an agent to open a tldraw.com board in a controlled Chrome tab and draw on it by executing JavaScript against the page's own editor, so edits sync to the shared board. It also captures PNG exports of the view, page, selection, or specific shapes.

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

Gives AI coding assistants live access to the Hyperiux Vault catalog of React and Next.js animation effects. Search effects, inspect dependencies and installation instructions, and retrieve source for free effects.

Read-only catalog of the @blueprint-modular/core design system (104 components). Four tools — list/search/get components and suggest compositions. Public, no auth, Streamable HTTP.

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.

Custom MCP server that lets AI control Autodesk Maya 2022+ directly, using code execution and self-discovery rather than hundreds of predefined tools. Includes structured tools for Unreal Engine asset preparation, validation, and FBX export.

Enables live preview of Storybook components inside the IDE as the AI edits them, using MCP Apps integration.

Enables searching thousands of device and print mockups and rendering screenshots or uploaded images into them via the Mockuuups Studio API.

Enables local image-driven displacement of STL/OBJ meshes, STL/3MF export, and agent-driven texturing workflows without remote services.

Enables designing labels for NIIMBOT thermal printers and previewing exactly what the printhead will burn, since each design is rendered offline with NiimBlue's own code in headless Chrome and returned as a 1-bit PNG with layout warnings. It also returns an open-in-app link so the label can be reviewed and printed from NiimBlue, without the server ever touching a printer.

Enables AI coding agents to retrieve mode and stage guidance so they can lead users through a 9-stage design workflow, including questions, required artifacts, exit criteria, dependencies, pitfalls, rollback impact, and environment requirements. It helps non-designers turn ideas into buildable HTML/WPF design specs while keeping the human in control of confirmation and revisions.

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 AI assistants to search a catalogue of plain HTML, CSS and JavaScript UI components and fetch each one's exact files, settings and framework integration instructions. Lets users add production-ready interface components by asking in natural language.

Loads your project's Tailwind CSS config and exposes tools for AI agents to query actual design tokens and validate class names, preventing hallucination of non-existent utilities.

Enables AI clients to control a running Blender instance through the Model Context Protocol, allowing scene inspection, object creation and editing, rendering, and execution of Blender Python. It works locally via a WebSocket bridge between the MCP server and a Blender add-on.