move tentra-mcp to Architecture & Design + v3 positioning

Relocate entry from Coding Agents to Architecture & Design to reflect
Tentra's primary positioning as an AI-native architecture platform
(diagram generation + 14-framework code export + drift detection).
Code-graph layer remains as a secondary feature.

README.md

@@ -256,6 +256,7 @@ Design and visualize software architecture, system diagrams, and technical docum
 - [erajasekar/ai-diagram-maker-mcp](https://github.com/erajasekar/ai-diagram-maker-mcp) [![erajasekar/ai-diagram-maker-mcp MCP server](https://glama.ai/mcp/servers/erajasekar/ai-diagram-maker-mcp/badges/score.svg)](https://glama.ai/mcp/servers/erajasekar/ai-diagram-maker-mcp) 📇 ☁️ 🏠 🍎 🪟 🐧 - MCP server for AI Diagram Maker — generate flowcharts, sequence diagrams, ERDs, system/network architecture, UML, mindmap, and workflow from natural language, code, ASCII, images, or Mermaid. Inline rendering using MCP Apps UI and editable diagram URLs. Requires API key.
 - [GittyBurstein/mermaid-mcp-server](https://github.com/GittyBurstein/mermaid-mcp-server) 🐍 ☁️ - MCP server that turns local projects or GitHub repositories into Mermaid diagrams and renders them via Kroki.
 - [Narasimhaponnada/mermaid-mcp](https://github.com/Narasimhaponnada/mermaid-mcp) 📇 ☁️ 🍎 🪟 🐧 - AI-powered Mermaid diagram generation with 22+ diagram types including flowcharts, sequence diagrams, class diagrams, ER diagrams, architecture diagrams, state machines, and more. Features 50+ pre-built templates, advanced layout engines, SVG/PNG/PDF exports, and seamless integration with GitHub Copilot, Claude, and any MCP-compatible client. Install via NPM: `npm install -g @narasimhaponnada/mermaid-mcp-server`
+- [rdanieli/tentra-mcp](https://github.com/rdanieli/tentra-mcp) [![rdanieli/tentra-mcp MCP server](https://glama.ai/mcp/servers/rdanieli/tentra-mcp/badges/score.svg)](https://glama.ai/mcp/servers/rdanieli/tentra-mcp) 📇 ☁️ 🏠 🍎 🪟 🐧 - AI-native architecture platform for engineering teams. Describe a system in natural language (e.g. "payment service with Stripe, Kafka, PostgreSQL") → get an interactive typed diagram with 167 cloud components → export to 14 production frameworks (Java Spring Boot, Python FastAPI, Go chi, Rust Axum, .NET, Kotlin Ktor, Ruby Rails, Elixir Phoenix, Docker Compose, Terraform, Mermaid, ADR, and more). Drift detection (`sync_architecture`) scores saved diagrams against live code 0–100 with a structured diff. 9 quality-lint rules catch orphans, SPOFs, god services. Also includes a secondary persistent code-graph layer for AI coding agents (free offline via `npx tentra-mcp --local init`). Agent-as-LLM pattern — zero LLM cost on our side, zero API key on yours. 35 MCP tools. Works in Cursor, Claude Code, Codex, Windsurf.
 
 ### <a name="bio"></a>Biology, Medicine and Bioinformatics
 - [ammawla/encode-toolkit](https://github.com/ammawla/encode-toolkit) [![encode-toolkit MCP server](https://glama.ai/mcp/servers/ammawla/encode-toolkit/badges/score.svg)](https://glama.ai/mcp/servers/ammawla/encode-toolkit) 🐧 - MCP server and Claude Plugin for a full ENCODE Project genomic data and analysis toolkit — search, download, track, and analyze functional genomics experiments.
@@ -465,7 +466,6 @@ Full coding agents that enable LLMs to read, edit, and execute code and solve ge
 - [OthmaneBlial/term_mcp_deepseek](https://github.com/OthmaneBlial/term_mcp_deepseek) 🐍 🏠 - A DeepSeek MCP-like Server for Terminal
 - [pdavis68/RepoMapper](https://github.com.mcas.ms/pdavis68/RepoMapper) 🐧 🪟 🍎 - An MCP server (and command-line tool) to provide a dynamic map of chat-related files from the repository with their function prototypes and related files in order of relevance. Based on the "Repo Map" functionality in Aider.chat
 - [preflight-dev/preflight](https://github.com/preflight-dev/preflight) 📇 🏠 🍎 🪟 🐧 - 24-tool MCP server for Claude Code that catches vague prompts before they waste tokens. Includes 12-category prompt scorecards, session history search with LanceDB vectors, cross-service contract awareness, correction pattern learning, and cost estimation.
-- [rdanieli/tentra-mcp](https://github.com/rdanieli/tentra-mcp) [![rdanieli/tentra-mcp MCP server](https://glama.ai/mcp/servers/rdanieli/tentra-mcp/badges/score.svg)](https://glama.ai/mcp/servers/rdanieli/tentra-mcp) 📇 ☁️ 🏠 🍎 🪟 🐧 - Persistent memory for AI coding agents. Indexes your repo into a queryable graph of files, symbols, imports, and call edges. Measured 99.4% token reduction on read-path queries (156.8× ratio) on our own monorepo. Agent-as-LLM pattern — zero LLM cost on our side, zero API key on yours. 33 MCP tools: 9 architecture + 4 code-graph write + 11 code-graph read (including find_references for safe refactors) + 9 enrichment (contracts, decisions, ownership, domains). Also generates AI architecture diagrams with 14-framework code export. Works in Cursor, Claude Code, Codex, Windsurf.
 - [religa/multi-mcp](https://github.com/religa/multi_mcp) 🐍 🍎 🪟 🐧 - Parallel multi-model code review, security analysis, and AI debate with ChatGPT, Claude, and Gemini. Orchestrates multiple LLMs for compare, consensus, and OWASP Top 10 security checks.
 - [rinadelph/Agent-MCP](https://github.com/rinadelph/Agent-MCP) 🐍 🏠 - A framework for creating multi-agent systems using MCP for coordinated AI collaboration, featuring task management, shared context, and RAG capabilities.
 - [shashankss1205/codegraphcontext](https://github.com/Shashankss1205/CodeGraphContext) 🐍 🏠 🍎 🪟 🐧 An MCP server that indexes local code into a graph database to provide context to AI assistants with a graphical code visualizations for humans.