"OCR agent" matching MCP servers:

Enables AI coding agents to design, analyze, and evaluate agent system designs against a curated catalog of agent patterns, with retrieval, scoring, and refinement workflows.

A TypeScript stdio MCP server that lets agents read, import, propose connections for, and apply optimistic patches to versioned agent-draw diagram documents.

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.

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 Umtri — give your AI coding agent a persistent map of your project's structure, dependencies, and bugs.

Generates editable Excalidraw diagrams from natural language system descriptions, with properly bound arrows and labels. Includes tools for diagram creation, validation, and backend status.

Enables analysis of any GitHub repository to get architecture, file roles, execution flows, system design Q\&A, and structured agent context. Works with MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.

Infers the architecture rules a TypeScript repo already follows from its import graph, with the evidence for each rule. Read-only tools to scan, recommend and explain rules, so an agent can check them before writing code.

Enables MCP clients to list, select, create, summarize, and edit ExcaliDash (Excalidraw) drawings through the Drawing Agent API, supporting both stdio and Streamable HTTP transport.

Enables an AI agent to join a live Excalidraw collaboration room as a headless participant, read the drawing in real time, and add or modify elements on the shared canvas.

An architecture consulting server that reviews multi-agent systems against a knowledge graph of patterns derived from expert literature. It provides grounded recommendations with chapter citations, maturity scoring, and interactive architecture diagrams to identify and fix structural gaps.

Serves reusable SDLC agent roles and review checklists over MCP, enabling AI coding agents to execute structured product analysis, solution architecture, code review, and release management tasks in GitHub-first projects.

Enables AI agents to turn codebase changes into animated, narrated presentations that open in a browser and update live as the agent builds them, including stepped diffs, sequence diagrams, and review feedback loops.

AI-powered 3D globe control via Model Context Protocol. Connect any MCP-compatible AI agent to CesiumJS — camera, layers, entities, spatial analysis through 19 natural language tools.

Enables generating BPMN 2.0 process models from natural language descriptions, YAML, or images via OCR, with templates, validation, and compatibility with tools like Bizagi Modeler and Camunda Modeler.

MCP bridge to live SysML v1 models in CATIA Magic / Cameo Systems Modeler (No Magic MSoSA). Lets Claude Code or any MCP agent query, audit, and edit MBSE models — blocks, requirements, diagrams, parametrics, traceability — over a local, air-gapped connection.

An MCP server implementing Spec-Driven Development workflows for AI-agent CLIs and IDEs like Claude Code and Cursor, enabling spec-first development with automated workflow guidance and quality checks.

A TypeScript-based MCP server that automatically generates structured technical presentation PPTX files via deck JSON and layout engine.

Enables visual collaboration with an AI agent on a codebase through a shared drawing canvas, where hand-drawn diagrams are inferred as editable structure over MCP.

Enables AI agents to maintain a living flowchart of a project with 14 MCP tools, auto-layout, and a zero-dependency HTML viewer, providing visual status tracking with 7 color-coded states.