"Updating GeoServer data from external web sources" matching MCP servers:

Provides deterministic, read-only design knowledge for AI coding agents to help them choose visual directions, plan UI states, and compose design tokens, all without network access.

Wraps the Live2D Cubism Editor's external application integration API as MCP tools, enabling AI agents to control Cubism Editor for modeling operations via natural language.

A Python MCP server that allows your agent to outsource HTML generation and rendering, storing artifacts in memory and supporting both full HTML and resource URIs.

Enables 2D irregular polygon nesting (bin-packing) with tools to design, preview, get reports, and export DXF files for laser cutting or CNC routing.

Enables agent-driven CAD design through deterministic source files (.kcad.ts), including model evaluation, validation, and export to STEP/STL via MCP tools for review and introspection.

An MCP server that enables AI agents to semantically retrieve premium UI components from Awwwards and adapt them into clean React + Tailwind code.

Enables external AI assistants and MCP clients to programmatically control Adobe Illustrator via WebSocket, supporting generative vector creation, layer organization, and document automation from natural language prompts.

Install premium, production-ready Three.js/WebGL 3D web components, templates and interactive scenes into Claude Code, Cursor & Codex. A hosted MCP for premium 3D web you own, from AETumi.

Enables MCP-compatible assistants to inspect and edit the open PCB in KiCad, including reading board info, footprints, nets, tracks, selection, and BOM data, as well as moving footprints, adding tracks and text, updating BOM fields, and saving the board.

Enables AI assistants to create interactive prototypes, annotate UI elements, generate PRDs, and track which annotations and documents need updating after changes.

Enables MCP clients to control EasyEDA Pro for schematic and PCB design through natural language, bridging the EasyEDA API without external AI or API keys.

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.

Enables coding agents to read, render, and normalize design documents from Figma and Adobe XD, providing visual context plus structured design data and generating starter code for web, React, Vue, Flutter, SwiftUI, and Jetpack Compose.

Enables AI-powered icon search, generation, and download from 275,000+ icons with web-based authentication and subscription plans.

STOP UI SLOP. Gives coding agents searchable evidence from 800,000+ real web and iOS screens, design contracts, and a hard UI finish gate.

Enables AI assistants to generate UI components and web interfaces from natural language descriptions using the Magic Patterns API.

Enables AI agents to compare design tokens from multiple sources, retrieve prior reconciliation runs, and get detailed per-conflict breakdowns with confidence factors and alias chains.

Enables Claude to draw on a live tldraw canvas from prompts, with real-time visualization in a browser. Provides tools for creating, updating, deleting shapes and retrieving canvas state.

AI assistants can read and inspect Figma design context locally via a plugin, without external API keys or rate limits.

Enables authoring, preview, and export of Spine 2D skeletal animations via natural language from Claude Code or any MCP client, with a web dashboard and tools for keyframing, templates, and GIF preview.