Add mcp-bastion (security proxy for MCP) to Security

README.md

@@ -3558,6 +3558,7 @@ Tools for conducting research, surveys, interviews, and data collection.
 - [atomicchonk/roadrecon_mcp_server](https://github.com/atomicchonk/roadrecon_mcp_server) 🐍 🪟 🏠 MCP server for analyzing ROADrecon gather results from Azure tenant enumeration
 - [mirajmahmudul/agentdevx-sdk](https://github.com/mirajmahmudul/agentdevx-sdk) [![mirajmahmudul/agentdevx-sdk MCP server](https://glama.ai/mcp/servers/mirajmahmudul/agentdevx-sdk/badges/score.svg)](https://glama.ai/mcp/servers/mirajmahmudul/agentdevx-sdk) 📇 ☁️ - Give your AI hands. Identity and credential vault gateway for autonomous agents. Ed25519 cryptographic identity (not OAuth), AES-256-GCM encrypted credential vault, OPA policy engine with full audit logging (captures allowed and denied actions), persistent per-agent memory, and web scraping tools. Self-bootstrapping — an agent can discover, register, and start calling tools with zero human setup. Register any API via OpenAPI spec.
 - [behrensd/mcp-firewall](https://github.com/behrensd/mcp-firewall) 📇 🏠 🍎 🪟 🐧 - Deterministic security proxy (iptables for MCP) that intercepts tool calls, enforces YAML policies, scans for secret leakage, and logs everything. No AI, no cloud.
+- [Gowthaman90/mcp-bastion](https://github.com/Gowthaman90/mcp-bastion) [![Gowthaman90/mcp-bastion MCP server](https://glama.ai/mcp/servers/Gowthaman90/mcp-bastion/badges/score.svg)](https://glama.ai/mcp/servers/Gowthaman90/mcp-bastion) 📇 🏠 🍎 🪟 🐧 - Reliability + security proxy that sits in front of MCP servers: TOFU tool-definition pinning against rug pulls, tool-poisoning and cross-server-exfiltration detection, argument/command-injection blocking, inline secret redaction, MCP 2026-07-28 header/body validation (`-32020`) and cache-policy clamping, and a compliance-mapped audit trail (NIST AI RMF / OWASP). Coverage measured on an open benchmark with a held-out corpus. `npx -y mcp-bastion`
 - [bluetieroperations-create/blackwall-mcp](https://github.com/bluetieroperations-create/blackwall-mcp) [![bluetieroperations-create/blackwall-mcp MCP server](https://glama.ai/mcp/servers/bluetieroperations-create/blackwall-mcp/badges/score.svg)](https://glama.ai/mcp/servers/bluetieroperations-create/blackwall-mcp) 📇 ☁️ - Pre-action risk gate for AI agents. One `forecast` tool the agent calls before any irreversible action (send money, run SQL, delete data); returns a risk score (0–100), reversibility class, named red flags from 28 failure modes, and a gate: proceed / confirm / human-required.
 - [Perufitlife/web-exposure-mcp](https://github.com/Perufitlife/web-exposure-mcp) [![Perufitlife/web-exposure-mcp MCP server](https://glama.ai/mcp/servers/Perufitlife/web-exposure-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Perufitlife/web-exposure-mcp) 📇 🏠 🍎 🪟 🐧 - Points an AI agent at a live URL and confirms publicly-served secret files by fetching the bytes — exposed `.git`, `.env`, JS source maps, backup/SQL dumps, directory listing, and dotfiles. Zero dependencies, read-only.
 - [Bichev/agentradar-mcp](https://github.com/Bichev/agentradar-mcp) [![Bichev/agentradar-mcp MCP server](https://glama.ai/mcp/servers/Bichev/agentradar-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Bichev/agentradar-mcp) 📇 ☁️ 🍎 🪟 🐧 - On-chain trust oracle for the ERC-8004 + x402 agent economy. 18 tools for verifying AI agents: 6-signal composite trust scoring (0-100), 272-wallet scam database, ERC-8004 identity lookup, EAS attestations on Base mainnet. x402-payable. Free `get_score` / `check_scam`. Live at [vvpro.ai](https://vvpro.ai) · npm [`@agentradar/mcp`](https://www.npmjs.com/package/@agentradar/mcp).