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

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.

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

A communication framework that enables multiple AI agents to collaborate through asynchronous messaging, agent registration, and discovery. It facilitates complex task coordination and real-time discussion across distributed agent workflows using the Model Context Protocol.

Unified MCP server integrating NIST and OWASP security frameworks with live vulnerability data, enabling security searches, compliance mapping, threat modeling, and checklist generation.

Enables MCP clients like Claude to query Chinese A-share market data, including K-line charts with forward/backward adjustment, limit-up and limit-down pools, per-stock fund flows, index quotes, and stock news, with automatic symbol normalization and retry handling for throttled data sources.

Provides A-share (Chinese stock market) quantitative analysis through tools for stock screening, northbound capital flow tracking, dragon-tiger list analysis, margin trading, sector analysis, technical indicators, IPO info, and limit-up/down statistics using akshare data.

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.

Enables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.

Enables academic research through paper search across multiple databases (IACR, CryptoBib, Crossref, Google Scholar), PDF processing, and GitHub repository browsing. Features modular architecture with FastMCP-based proxy server routing to specialized academic tools.

An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.

Enables high-craft web design and engineering through OKLCH color systems, fluid typography, Three.js 3D scenes, frontend security audits, multi-viewport capture, and Python-backed design verification.

A local-first FastMCP server that indexes offline frontend catalogs (components, patterns, motion libraries) and exposes discover, search, compare, and recommend tools to AI agents via stdio.

Read-only MySQL MCP server that lets AI agents list tables, describe schemas, and run SELECT/SHOW/EXPLAIN queries with a row cap, bound to a single database for safety.

Enables AI assistants to retrieve and cite South Korean national construction standards (KDS/KCS) with tables and formula images via the KCSC OpenAPI, and to use design decision trees, validation, and blank Excel templates directly in the chat interface.

Enables AI agents to search, retrieve, and navigate Apple's Human Interface Guidelines as live Markdown content across all Apple platforms.

MCP server bridging ChatGPT-compatible clients to the Design Flow System, enabling project session management, draft import, round locking, and read-only access to design state and traceability.

Enables assistants to discover, search, and extract real design systems — palettes, type scales, spacing, surfaces, and do/don't guidance — from the public style pages of styles.refero.design. It reports index coverage with every search and renders matched styles as structured design.md sections or parsed JSON tokens.

Bridges Design OS exported component packages into target projects, handling migrations across different CSS, component, and icon libraries.

Contract-driven test enforcement and reporting for LLM-generated code via MCP, VS Code, Copilot CLI, Claude, Cursor, or Python SDK.

Enables AI hosts to validate, write to disk, hot-reload, preview, and export single-file HTML prototypes built to the Spark OP design spec, serving them locally at 127.0.0.1:5179 by slug. Also bundles the triggering skill, spec references, templates, and CSS tokens so agents can create, revise, and hand off development-ready prototype HTML through one controlled output path.