"An overview of OSINT (Open Source Intelligence)" matching MCP servers:

Enables AI assistants to read and create geometry in an open Cadwork 3D document via a local bridge, with queued sequential execution, write approvals, undo support, and a live dashboard for monitoring activity.

Enables natural language control of Blender 3D through local AI models, allowing MCP clients to create, modify, and render scenes, apply materials, and execute Python code in Blender.

Enables MCP clients to inspect and export OpenPencil .fig and .pen files directly from disk, supporting operations like info, tree traversal, XPath queries, linting, and conversion to various formats without the desktop app or CLI.

Enforces agent design system compliance with tools to check guards, explain gaps, issue receipts, suggest fixes, and export audits.

Enables MCP-compatible AI clients to read and modify the user's currently open Figma file by executing JavaScript in Figma's sandbox, all through a local bridge with status monitoring, node jumping, and automatic rollback on errors.

Enables natural language control of AutoCAD drawings via LLMs like Claude, supporting drawing, layer management, and SQLite-backed entity analysis.

Enables querying PCB and schematic data and driving DelphiScript automation in Altium Designer via MCP.

Enables AI assistants to control Adobe After Effects through the MCP protocol, including composition creation, layer management, and animation.

An MCP server that simplifies Figma design data, generates code in multiple frameworks, and provides accessibility audits and drift detection, all using a free Figma Personal Access Token without a paid Dev Mode seat.

Enables AI assistants to interact with the Cocos Creator editor through the Model Context Protocol, providing 50 core tools for editor functionality.

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.

Enables searching, indexing, linking, and downloading 2000+ open-source fonts from fontsource.org, with support for font subsets, weights, styles, variable fonts, and CSS integration.

MCP server for Uiverse.io that lets AI agents browse, search, and fetch open-source UI components (HTML + CSS) directly in their editor. No API key required, it indexes 3,800+ components locally.

Enables running bpy Python code in an already-open Blender instance, with tools for health checks, scene info, and viewport screenshots.

Open-source dotted maps and animated 3D globes. Pick one of 21 looks for a country or the world, build share links, open and edit a pasted link, and get embed code. Hosted at https://globestudio.app/mcp or run with npx @globestudio/mcp. Free, MIT, no API key.

Provides deterministic UI/UX intelligence and systems performance auditing tools for AI coding agents, enabling generation of accessible, well-designed React/Tailwind interfaces and elimination of backend anti-patterns like N+1 queries and sequential waterfalls.

Provides two MCP servers: Variant Authority for managing component variant manifests and Radix Primitives for accessibility composition using Radix UI. Together they serve as the source of truth for design-to-code workflows.

An MCP server that exposes an open Autodesk Revit model to MCP clients, enabling natural language inspection and editing of the model via Revit API calls through pyRevit Routes.

Provides access to Iconify's 200,000+ open source vector icons from 200+ icon sets, enabling search, browsing, and retrieval of icon data with framework usage examples.

Enables an AI agent to drive a live Blender session, building, sculpting, measuring, checking, rigging, lighting, rendering and exporting 3D models through safe operations in world units. Every geometry-changing call reports achieved dimensions, open edges and failures as numbers and review images, so modelling mistakes become visible instead of silent.