Search

Audits the MCP servers configured on a machine for supply-chain risk: unpinned versions, inline secrets, missing provenance, install scripts, maintenance signals

Vet AI components (skills, rules files, MCP servers, plugins) on your own laptop, offline by default.

A calibrated firewall for AI agent tool calls: screens them before they run, and screens tool results before the agent reads them. Covers MCP servers through a proxy and a client's built-in tools through a hooks adapter.

The first MCP server that verifies AI outputs in real-time with 6-dimension contract validation and multi-provider failover

Decision infrastructure for autonomous AI agents: evaluates a proposed blockchain action intent and returns an explainable ALLOW/WARN/BLOCK decision before execution, signed as a verifiable OAA token.

[](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.

Offensive security framework for AI agents and MCP servers

Runtime proxy for MCP security, cost governance & audit

Security and context auditor for AI agents and MCP servers.

Security defaults for Claude Code — clean context, locked-down credentials, guarded egress.

The open cybersecurity harness — evidence-first, agent-driven security research for authorized targets.

AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.

Transparent MCP security proxy: tool metadata integrity, call validation, and response analysis. Apache-2.0.

Zero-trust prompt injection security gate & MCP server for AI agents (Cursor, Claude Code, Antigravity, OpenCode, Codex)

Security scanner for AI agents and MCP servers — finds exfiltration paths, unauthenticated tool exposure, code execution risks, and misconfigured agents

AI-first security scanner with 79 analyzers, 9,600+ detection rules, and intelligent false positive reduction for AI/ML, LLM agents, and MCP servers

Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.

Security scanner for Model Context Protocol (MCP) servers

Offline-first security scanner and trust registry for MCP servers.

Open-source AWS security scanner. 45 checks, each with a ready-to-use fix.