diff --git a/README.md b/README.md
index 054679972..0bb10d065 100644
--- a/README.md
+++ b/README.md
@@ -3817,6 +3817,7 @@ Tools for conducting research, surveys, interviews, and data collection.
 - [juanisidoro/securecode-mcp](https://github.com/juanisidoro/securecode-mcp) [![securecode-mcp MCP server](https://glama.ai/mcp/servers/juanisidoro/securecode-mcp/badges/score.svg)](https://glama.ai/mcp/servers/juanisidoro/securecode-mcp) 📇 ☁️ 🍎 🪟 🐧 - Secrets vault for Claude Code with audit logs, MCP access rules, and AES-256 encryption. Secrets are injected to local files so the AI never sees raw values. Includes session lock, device approval, and per-model access policies.
 - [ndl-systems/kevros-mcp](https://github.com/ndl-systems/kevros-mcp) [![kevros-mcp MCP server](https://glama.ai/mcp/servers/@ndl-systems/kevros-mcp/badges/score.svg)](https://glama.ai/mcp/servers/@ndl-systems/kevros-mcp) 🐍 ☁️ - Governance primitives for autonomous agents — verify actions against policy, record signed provenance, and bind intents cryptographically. Free tier: 100 calls/month.
 - [LaurieWired/GhidraMCP](https://github.com/LaurieWired/GhidraMCP) ☕ 🏠 - A Model Context Protocol server for Ghidra that enables LLMs to autonomously reverse engineer applications. Provides tools for decompiling binaries, renaming methods and data, and listing methods, classes, imports, and exports.
+- [luiacuaniello/perspectivegraph](https://github.com/luiacuaniello/perspectivegraph) [![luiacuaniello/perspectivegraph MCP server](https://glama.ai/mcp/servers/luiacuaniello/perspectivegraph/badges/score.svg)](https://glama.ai/mcp/servers/luiacuaniello/perspectivegraph) 🎖️ 🏎️ 🏠 🍎 🪟 🐧 - Attack-path engine for cloud and Kubernetes. Eight read-only tools let an agent list the reachable routes from internet exposure to sensitive assets, explain each hop and the evidence behind its probability, find choke points, and simulate cutting a relationship before recommending the fix. Connects to a running PerspectiveGraph: `perspectivegraph mcp --api http://localhost:8080`.
 - [mariocandela/beelzebub](https://github.com/mariocandela/beelzebub) ☁️ - Beelzebub is a honeypot framework that lets you build honeypot tools using MCP. Its purpose is to detect prompt injection or malicious agent behavior. The underlying idea is to provide the agent with tools it would never use in its normal work.
 - [mobb-dev/mobb-vibe-shield-mcp](https://github.com/mobb-dev/bugsy?tab=readme-ov-file#model-context-protocol-mcp-server) 🎖️ 📇 ☁️ 🍎 🪟 🐧 - [Mobb Vibe Shield](https://vibe.mobb.ai/) identifies and remediates vulnerabilities in both human and AI-written code, ensuring your applications remain secure without slowing development.
 - [MoltyCel/moltrust-mcp-server](https://github.com/MoltyCel/moltrust-mcp-server) [![moltrust-mcp-server MCP server](https://glama.ai/mcp/servers/@MoltyCel/moltrust-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/@MoltyCel/moltrust-mcp-server) 🐍 ☁️ 🍎 🪟 🐧 - Trust infrastructure for AI agents — register DIDs, verify identities, query reputation scores, rate agents, manage W3C Verifiable Credentials, and handle USDC credit deposits on Base.