Add Apature bastion (design review)

README.md

@@ -1057,6 +1057,7 @@ Data Platforms for data integration, transformation and pipeline orchestration.
 - [hivemindunit/llmintel-mcp](https://github.com/hivemindunit/llmintel-mcp) [![hivemindunit/llmintel-mcp MCP server](https://glama.ai/mcp/servers/hivemindunit/llmintel-mcp/badges/score.svg)](https://glama.ai/mcp/servers/hivemindunit/llmintel-mcp) 📇 ☁️ - Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to. Covers OpenAI, Anthropic, Azure, Bedrock, Google, and Cohere. No API key. `npx -y @llmintel/mcp` or `https://llmintel.ai/v1/mcp`
 - [rm-rf-prod/GroundTruth-MCP](https://github.com/rm-rf-prod/GroundTruth-MCP) [![rm-rf-prod/GroundTruth-MCP MCP server](https://glama.ai/mcp/servers/rm-rf-prod/GroundTruth-MCP/badges/score.svg)](https://glama.ai/mcp/servers/rm-rf-prod/GroundTruth-MCP) 📇 🏠 🍎 🪟 🐧 - Self-hosted MCP for live docs, code audits, snippets, and best practices across 445+ libraries. 14 tools, 107 audit patterns with file:line precision, BM25-ranked snippets, lockfile-aware version pinning, npm/PyPI/crates.io/Go fallback. No API keys, no rate limits, Context7 alternative. `npx -y @groundtruth-mcp/gt-mcp`
 - [scarletkc/vexor](https://github.com/scarletkc/vexor) [![scarletkc/vexor MCP server](https://glama.ai/mcp/servers/scarletkc/vexor/badges/score.svg)](https://glama.ai/mcp/servers/scarletkc/vexor) 🐍 🏠 ☁️ 🍎 🪟 🐧 - A semantic search engine for files and code — find files by describing what they do, not their names. Local reusable indexes, configurable embedding providers (OpenAI, Gemini, Voyage, any OpenAI-compatible API, or fully offline local models), AST-aware code chunking, optional reranking. `uvx vexor mcp` or `pip install vexor`.
+- [apatureai/bastion](https://github.com/apatureai/bastion) [![apatureai/bastion MCP server](https://glama.ai/mcp/servers/apatureai/bastion/badges/score.svg)](https://glama.ai/mcp/servers/apatureai/bastion) 📇 🏠 - In-loop design review of rendered UI for coding agents: submit a preview URL, get grounded findings with element references, then recheck the fix. Read-only by design — never edits code. OAuth 2.1 and SSRF-safe URL handling reference implementation. `npx -y @apatureai/bastion`
 - [aradar46/reuse-before-generate](https://github.com/aradar46/reuse-before-generate) [![aradar46/reuse-before-generate MCP server](https://glama.ai/mcp/servers/aradar46/reuse-before-generate/badges/score.svg)](https://glama.ai/mcp/servers/aradar46/reuse-before-generate) 📇 🏠 🍎 🪟 🐧 - Checks whether a project idea already exists before your agent scaffolds it. Searches GitHub, npm and Python repos, drops archived/inactive results, and returns at most 3 maintained alternatives with a concrete "extend this instead" suggestion for each. The calling agent does the relevance judgement itself, so no extra API key is needed. `npx -y reuse-before-generate`
 - [hernaninverso/eleata-verify-mcp](https://github.com/hernaninverso/eleata-verify-mcp) [![hernaninverso/eleata-verify-mcp MCP server](https://glama.ai/mcp/servers/hernaninverso/eleata-verify-mcp/badges/score.svg)](https://glama.ai/mcp/servers/hernaninverso/eleata-verify-mcp) 📇 ☁️ - Grounding / hallucination guard: verify a claim against evidence (Supported/Refuted/Not Enough Evidence) with a confidence + abstain flag, for RAG and agents. `npx -y eleata-verify-mcp`.
 - [appcreationsca/bumpguard-mcp](https://github.com/appcreationsca/bumpguard-mcp) [![appcreationsca/bumpguard-mcp MCP server](https://glama.ai/mcp/servers/appcreationsca/bumpguard-mcp/badges/score.svg)](https://glama.ai/mcp/servers/appcreationsca/bumpguard-mcp) 🐍 🏠 🍎 🪟 🐧 - Pre-flight dependency-upgrade impact analysis: reports exactly which of your code's API usages break *before* you bump a dependency, with line numbers, severity, and fix hints. Also verifies AI-written code against the actually-installed API to catch hallucinated calls. Static analysis only — never runs third-party code. Python + .NET. `pip install bumpguard-mcp`