"Exposing a markdown folder as an MCP server for Claude" matching MCP servers:

A lightweight sketch canvas that lets users draw ideas and sync them in real-time to AI via MCP, enabling visual communication without exports.

Exposes 20+ tools that let any MCP-compatible client search patent rules and statutes (MPEP, USC, CFR) with hybrid RAG retrieval, hunt prior art across 100M+ patents via Google BigQuery, run automated claims and application compliance checks, and generate patent-style diagrams. It also provides CLI-driven setup, GPU-accelerated indexing, and health reporting so users can move from a raw invention description to a reviewable draft application.

Translates natural language commands into structured geometric operations for a simulated CAD engine using LLMs. It enables users to create shapes, modify dimensions, and perform 3D operations like extrusion through the Model Context Protocol.

Enables Claude to draw Mermaid diagrams as live, inline canvases in the reply instead of printing them as code blocks. The rendered diagram can be zoomed, panned, re-themed, expanded in height, and flipped to a highlighted, copyable source view.

Enforces a rigorous spec-driven engineering workflow for AI coding assistants, requiring requirements, design, and task planning before any code is written.

Provides UI architecture analysis for converting Figma designs or web pages into reusable UI code blocks with effort estimation in CSV format.

A design orchestrator that brings Superdesign capabilities to Claude Code as native tools, enabling AI-powered UI design, wireframing, component creation, and logo/icon generation without requiring Anthropic API keys.

BlenderMCP enables Claude AI to directly interact with and control Blender for prompt-assisted 3D modeling, scene creation, and manipulation. It supports object and material control, scene inspection, and execution of Python code through natural language commands.

A prescriptive template for building large MCP servers (20+ tools) organized as a tiered catalog with a broker, exposing exactly 7 tools to AI clients regardless of catalog size.

An MCP server that turns a folder of Markdown ADRs into live tools for AI agents: search, author, validate, link, and trace architectural decisions, with preview-by-default writes.

Turns a rambling app idea into a structured planning canvas of screens, flows, systems, data and open questions inside an existing Claude Code or Codex session, then writes the settled plan back to that session as a spec to build from. Plans are stored in the project's .doan/ folder alongside the code.

Validates and renders declarative JSON diagram specs to themeable SVG. The format has no coordinates, so a model writes structure and the renderer does the layout; tools: validate, render, kinds.

Offline MCP server for SAP ABAP static analysis, ABAP Cloud readiness scoring, and RAP scaffolding. It enables AI agents to lint ABAP source, compare reworks, check released APIs, and generate RAP business objects without needing an SAP system.

Deterministic "Rack-as-Code" 3D/2D CAD planner, 5-stage physical/PoE/acoustic validator, and parametric OpenSCAD/STL 3D-print generator for 10-inch mini-racks and 19-inch homelabs.

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.

15 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.

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.

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.

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

Enables coding agents to write repository documents (READMEs, RFCs, design docs, ADRs) from verified codebase facts, using a separate model for drafting and agent fact-checking for accuracy.

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.

Model Context Protocol (MCP) server for @imqueue — lets AI coding agents (Claude Code, Cursor and others) search the docs, scaffold typed services & clients and use @imqueue/cli live.

Enables desktop MCP clients to launch a local connector that renders Mermaid flowcharts from an AI assistant into a browser-based reader served on localhost. Users can explore a diagram step by step, inspect a step's incoming and outgoing connections, read relationships as text, and save the Mermaid source.

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

Enables Claude and Claude Code to scan local repositories, generate interactive architecture maps, and trace transitive callers to assess change impact.