"Creating a Framework Design in Draw.io" matching MCP servers:

Enables local Draw.io diagram creation, editing, and export via MCP tools, using the desktop app.

A configurable MCP server that enables creating custom analysis tools through JSON configuration, with built-in frameworks for error handling, self-evaluation, security guardrails, and output artifacts.

Enables to perform mathematical calculations, retrieve weather information, and manage files through a standardized MCP interface, showcasing best practices for building MCP servers.

Manages design tokens (colors, spacing, fonts) in a JSON file and enables agents to read, write, export, and detect drift between tokens and CSS via MCP.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

Provides read-only access to over 100 UX/UI design checklists from Checklist.design, enabling users to search and retrieve design guidance for specific flows and screens. Runs locally without an API key.

Provides software design guidance via MCP, including SOLID principles, design patterns, pattern scaffolding, and heuristic code-smell detection to help review and refactor code.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

A local stdio MCP server that enables AI coding tools to search and retrieve reusable interactive and motion design parts from a design-notes library, returning each part's notes, anchors, extracted parameters, and the absolute path to its self-contained index.html source. It also serves the original README provenance and source URLs for a given note.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.

Exposes iDRAC design-system knowledge via a single get_component tool, currently returning placeholder data for known components.

Bridges Claude Design projects into existing Claude Desktop sessions by fetching code files, chat history, and project bundles.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Captures webpage styles and HTML, converts CSS to Tailwind, and applies extracted designs to frontend frameworks like React.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

An MCP server that drives Anthropic's Claude Design from agentic coding CLIs, providing tools to create, generate, iterate, and export design systems without a browser.

Unofficial stdio MCP proxy for Anthropic's Claude Design MCP. Enables using Claude Design with any MCP host like Cursor, Claude Code, or Codex.

Creates a local MCP runtime for design-system repositories, enabling AI coding agents to look up and use real components, icons, and tokens instead of guessing.

Provides a reusable MCP server foundation with explicit tool registration, operation-mode separation, scope-based permissions, structured results, and built-in health/status tools.