"Searching PubMed references and formatting them in Markdown" matching MCP servers:

Enables users to create, validate, view, and export system stock-and-flow maps from a versioned JSON model through MCP-capable hosts over local stdio or hosted Streamable HTTP. Supports causal-loop and nested-level mapping while keeping submitted model content with the caller and requiring no LLM provider key.

Enables generating documentation from source code and templates, building API references from OpenAPI specs, creating architecture diagrams, and searching, versioning, and exporting documents. Supports multiple output formats including Markdown, HTML, PDF, and DOCX.

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.

Enables AI coding agents to list, read, create, update, delete, and render PlantUML and Mermaid diagrams, and check them against the actual codebase to detect architecture drift.

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.

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.

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 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.

Enables AI assistants to interact with Autodesk Civil 3D, allowing them to retrieve project data, create/modify/delete drawing elements, and execute code to automate Civil 3D operations.

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

Enables AI coding agents to discover, convert, and synchronize Draw.io C4 and UML diagrams into Mermaid Markdown, providing architectural context and guardrails during chat sessions.

Official draw.io MCP server: create diagrams from Mermaid, XML or CSV, shown inline in Claude, ChatGPT, VS Code and Cursor or opened in the draw.io editor. Searches 10,000+ shapes.

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.

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.

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.

Compiles 10 languages into a local AST and Stack Graphs relational index, exposing 12 MCP tools for sub-50ms blast-radius, centrality, and pathfinding queries that cut agent context token burn by ~85%. It also enforces architectural compliance through in-memory Virtual AST workspaces, embedded Datalog policy proofs, zero-config Louvain modularity (ΔQ) gates, and post-edit scope-creep audits.

Converts Markdown files into professional diagrams such as flowcharts, mind maps, and architecture diagrams using Mermaid.js and custom SVG renderers. It enables users to list, render, and export visualizations in multiple formats including SVG, PNG, and PDF.

Lets agents construct Mermaid diagrams from structured JSON IR and render them as PNG or SVG.

Enables assistants to turn a plain-language process description into a checked BPMN swimlane diagram, asking only for missing details and showing a picture for approval. Once approved, it exports the diagram as SVG, PNG and a .bpmn file that opens in Camunda, all drawn and checked locally on the user's own computer.

Enables agents to read, edit, validate, and simulate Poietic Stock and Flow designs by driving the poietic CLI, allowing collaborative work with humans in Poietic Playground.

Enables Claude Desktop and Claude Code to build, update, inspect, validate and compile workflows for the SOLVE-IT Workflow Builder from natural language, automatically laying out nodes and connections and checking them against the SOLVE-IT knowledge base. Each result is written as a JSON file for import into the builder, or returned as a share link when small enough.

diagramzu-mcp lets an AI client (Claude, Cursor, ChatGPT, etc.) author Mermaid diagrams in a shared workspace that a team can read, comment on, embed, and present at a clean URL — rather than just generating a one-off diagram. Hosted endpoint https://mcp.diagramzu.ai/mcp or local npx -y @diagramzu/mcp. Also listed in the official MCP registry as ai.diagramzu/mcp.

@codapult/guard is local-first, model-agnostic architecture guardrail software for AI coding agents. Use it to detect architectural drift, enforce approved software architecture rules, and check code changes in JavaScript and TypeScript projects.

Gives terminal coding agents a local browser canvas for rendering charts, tables, metrics, markdown, live widgets and sandboxed MCP App UIs that would otherwise reach them as raw JSON. Lets agents pose blocking visual multiple-choice questions and read back the user's clicks, selections and an animated architecture map of file activity.

An MCP server that recommends tech stacks for your project. Describe what you're building and get a recommended stack with reasoning, tradeoffs, and what each layer should use.

An MCP server that enables LLMs to create and open diagrams in draw.io using XML, Mermaid, or CSV formats, by building a URL with compressed content and opening it in the browser.

Enables Claude to generate PlantUML diagrams from natural-language requests and render them directly in chat as PNG, SVG, or ASCII art, with syntax-error feedback, shareable URLs, and URL decoding.

Tracks architectural decisions with testable predictions, outcome validation, and in-band feedback nudges to close decision loops for AI agents and teams.