"Adding functionality to large language models" matching MCP servers:

Turn natural language into 3D models in Fusion 360. 64 CAD tools including sketches, extrudes, fillets,and JIS standard parts.

An MCP server that adds engineering discipline to AI-assisted development, enforcing evidence-gated TDD, security review, backup strategy, and deployment generation to turn AI-generated code into production-ready software.

Enables AI agents like Claude to interact with Figma designs through 50+ tools for creating, styling, and manipulating design elements, components, and variables via a WebSocket relay and Figma plugin.

Enables an agent to turn a paper's draft into editable Figma frames for publication-ready figures, checking every number against the paper and verifying the exported PDF.

An MCP server that enables AI assistants to interact with Figma designs for tasks like reading document info, creating elements, and managing auto layouts. It facilitates real-time design automation via a custom Figma plugin and WebSocket server integration.

Enables creation of complete metamodels and model instances through natural language interaction by connecting Large Language Models to the MM-AR metamodeling platform.

Enables AI models and browser users to collaboratively create and edit a shared freeform canvas of positioned cards and directed connections, with tools for adding, updating, linking, and exporting boards as JSON or SVG.

Cloud infrastructure provisioning via natural language. Enables deploying production-ready infrastructure on AWS, GCP, Azure, or Oracle with a single prompt.

Enables LLMs to search and retrieve official Cisco network diagram icons as RGB PNG images, with metadata and category listing tools for building topology diagrams.

Provides systems thinking models as composable analysis lenses for architecture, infrastructure, DevOps, incident analysis, and technical decision-making.

An MCP server that builds a local webpage to view AI plans, reports, and diagrams, so the AI only needs to send a URL pointer instead of long text. It provides three tools (view_plan, view_report, view_diagram) and tracks project changes for diff viewing.

A read-only MCP server that gives AI agents access to Sparx Enterprise Architect models, enabling search, navigation, and reading of elements, packages, scenarios, and connectors from .qea exports without a running EA instance.

AI-native architecture diagramming for MCP clients (Claude Code, Cursor, Windsurf). The calling agent authors the graph (nodes, groups, edges); Flowgraf validates it, lays it out deterministically with ELK, renders an SVG + Mermaid, and returns a link to a live, editable canvas you can refine by chat, drag, or one-click AI design review. Agent-authored ops — no API key and no LLM cost to the calle

MCP server for AI Diagram Maker — generate software engineering diagrams from natural language, code, ASCII diagram, images, or Mermaid. Inline diagram rendering using MCP apps UI and diagram URL in responses. Works with Cursor, Claude Desktop, Claude Code, and any MCP-compatible AI.

Enables MCP-capable coding agents to access SkeletIQ architecture releases, including reading designs and build orders, generating and critiquing architectures, and reporting build progress and drift.

Renders diagram-as-code to PNG files on your disk, and also provides text-art previews and syntax validation, all locally without a browser or network.

Gives AI agents instant access to software architecture, dependencies, and impact analysis through pre-computed sgraph models, replacing dozens of grep/read cycles with a single tool call.

A comment-based spec-driven development MCP server that facilitates workflows from requirements creation to implementation via AI, using @spec-impl markers.

Generates professional architecture diagrams from natural language descriptions using template-driven prompts and swappable AI image providers.

A graph layout server that computes node coordinates and edge paths from structure using elkjs, enabling agents to offload layout calculations without rendering.