"Top 100 MCP Servers Ranked by Weekly Downloads" matching MCP servers:

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

Lets Claude Code, Cursor, VS Code and other AI agents draw and edit draw.io diagrams from your project's files, on a live browser canvas you can also edit by hand. Includes version history, undo, cloud shape libraries (AWS, Azure, GCP) and PNG or SVG export.

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.

Local code-graph engine for AI coding workflows: static analysis of Rust, Cangjie, ArkTS, TypeScript/JavaScript, C/C++, Python, and Shell projects into symbols, imports, call graphs, and quality gates, with pre-commit change review and impact analysis. Read-only by design — never executes build scripts or uploads code.

Enables AI coding agents to make evidence-aware design-pattern decisions by analyzing cases, comparing options, detecting misuse, stress-testing assumptions, planning adoption, writing ADRs, and generating evidence plans with transparent scoring.

Turns messy operational documents, SOPs, incident playbooks, spreadsheets, and business communications into faithful, source-grounded visual workflows directly inside Claude Desktop, Cursor, Zed, Windsurf, or any MCP-compatible agent. It also supports revising existing workflow graphs while preserving citation integrity and retrieving stored visual artifacts by ID.

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 a coding agent to sketch explanations step by step on a shared hand-drawn canvas beside the chat, highlighting parts as it talks and reading back anything the user draws or notes. Boards persist per chat and can be searched, saved, and exported as Excalidraw files or PNGs.

Enables AI agents to create, validate, and manage buildingSMART IDS (Information Delivery Specification) files with 100% compliance to the IDS 1.0 standard using IfcOpenShell's IfcTester library.

Semantic React/TSX analysis MCP server that saves 70-90% tokens by using AST to retrieve precise component usages, prop flow, and state update information for AI coding assistants.

Provides AI coding agents with durable architecture memory for repositories by generating structured project maps of responsibilities, relationships, and risks.

Score your agent's governance (0-100), lint MCP tool definitions, and estimate costs across all major models. Free diagnostic tools with no API key needed. Expert skill files on governance, economics, and system architecture available with free tier.

Enables creation of complete metamodels and model instances through natural language interaction by connecting Large Language Models to the MM-AR metamodeling platform.

Prevents premature AI coding by transforming vague product ideas into structured specifications, architecture decisions, and acceptance criteria through a series of interrogation and compilation tools.

An MCP server that designs software projects by drafting design documents with an LLM, refining them, answering questions, and creating projects via the AI2DEV API.

MCP server for generating and validating FrameIO modules and plugins, with code generation, validation, examples, and step-by-step guidance.

Enables AI clients and agents to turn a new idea into a structured set of clarifying questions, technology options, upward design breakdowns, reverse reasoning, and risk assessments so users can steer top-level design decisions. It also supports saving insights and building a bidirectional design tree of concepts and their implementations.

Enables managing Architecture Decision Records by showing the ADR directory, listing existing ADR files, and generating new ADR markdown stubs via natural language.

Enables agents to search a public catalog of published components, estimate what a data model would reuse, mint, and cost, then assemble, publish, and generate the resulting package or application. Spending is gated by a shown estimate and the key's limit, so no build or charge happens without review.

A private-by-default, local-first DAG editor that lets you build causal diagrams visually, validate cycles, and save/export as JSON, SVG, or PNG through MCP tools.

Enables AI agents to plan software collaboratively with humans by creating and editing graph structures over MCP, then exporting them as Markdown trees and Obsidian Canvas files.

Enables AI agents to visualize tasks on a collaborative Sketchbord whiteboard by composing content into diagrams, editing them incrementally, and reading back the board including user-drawn additions.

Static codebase analysis as MCP tools — give AI coding agents a map of your repo instead of letting them burn half their tokens rediscovering it file by file.

Lets Claude Code and other agents generate Chen-notation ER diagrams from SQL DDL or SQLAlchemy sources, then read the model, apply edits, re-layout, check for crossings and missing columns, and export PNG/SVG/draw.io. Changes made by the agent refresh any open graphical editor in real time.

Enables autonomous software engineering workflows by routing intent to specialized modes, managing Fable5 task ledgers and backend contracts, auditing React/TypeScript stacks, generating architectural SVG diagrams, and enforcing write-guard path policies.

Enables coding agents to navigate and score brownfield multi-service flows by mapping use-case trees, tracing loadouts and consumers, and detecting drift.

A semantic map of your .NET solution for AI coding agents. Analyzes a solution with Roslyn into a queryable code graph exposing 11 read-only tools (find_symbol, impact_analysis, find_implementations, etc.) over MCP. 100% local, no telemetry, MIT licensed.

Enables AI clients to inspect and make targeted, revision-checked edits to Excalidraw class diagrams stored in a local Obsidian vault, including adding, moving, rewiring, resizing, and deleting shapes, text, and arrows. It supports low-level design review by summarizing classes and relationships, and confines access to a configured folder while backing up drawings before each change.

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.

Enables Claude to turn a public or private code repository into an interactive, in-chat graph of its folders, files, classes, functions and API endpoints, including the calls, imports, tests and HTTP requests linking them, which users can pan, search, filter and click through. Provides tools for exploring a node's callers, callees and tests, searching nodes by name, path or docstring, and optionally writing the graph into Neo4j.