"Overview and Applications of Mixture of Experts in Machine Learning" matching MCP servers:

Enables developers and product owners to scan a codebase and extract a readable business overview—features, roles, access control, data model, and endpoints—along with findings on missing or inconsistent rules, and generate shareable HTML or Markdown reports and diagrams.

Enables validating, simulating, and analyzing finite state machines via MCP tools for step execution, path finding, and schema inspection.

MCP server for creating and editing diagrams using draw.io. Allows generating diagrams from Mermaid or XML, searching shapes, and opening them in draw.io for export.

13 AI-powered UML diagram tools for coding agents. Generates class, sequence, state, ER, threat model, deployment and architecture diagrams in Mermaid syntax. Works in Claude Code, Cursor and Windsurf.

Enables rendering, validation, formatting, and inspection of D2 diagrams via the Model Context Protocol, using WASM for rendering without requiring the d2 binary.

A Model Context Protocol server that gives an LLM a structured visual layer to describe what exists and get back a clean, precise SVG diagram instead of ASCII art.

🐍 🏠 - Code graph for AI agents over MCP: resolves Python and TypeScript calls to fully qualified names and reports the share it could not resolve instead of guessing. Multi-hop impact analysis, authz reachability audit, architectural drift against declared patterns. Local, SQLite. uvx codegraph-brain

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.

Enables generating, reading, auditing, and previewing BPMN 2.0 diagrams for Bizagi Modeler, with an automatic layout engine that produces files Bizagi can open, plus optional control of the Bizagi Modeler desktop app on Windows.

Enables auto-configuration and validation of React components against a glassmorphic design token system using an AST correction engine. It supports managing UI presets, enforcing design uniformity in Monaco IDE, and exporting tokens as CSS, Tailwind, or JavaScript variables.

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.

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 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.

An MCP server that generates diagrams from Mermaid code in multiple formats (PNG, PDF, SVG).

MCP server that provides a live, terminal-native layered dependency map for AI coding assistants, with tools to track and visualize development progress in real time.

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.

Provides enterprise architecture knowledge tools that ground agents in curated patterns, enabling translation of messy enterprise asks into realistic architecture recommendations, platform selection, risk checks, and brand context retrieval.

A single, queryable source of engineering constraints that coding agents consult at code-generation time, exposed over an MCP server.

Enables two coding agents to deliberate on a plan in a shared room, taking turns to argue and converge until the lead writes a spec file and closes the room.

Render hierarchical system diagrams as PNGs from YAML definitions using a four-level ontology of networks, factories, machines, and nodes.