Security Scanning

LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails

The deterministic attack-surface perception layer for AI security agents

Checks ML model files (pickle, PyTorch, joblib, NumPy, GGUF, ONNX) for code that runs on load.

Measure MCP servers, pin the approved tool surface, refuse calls to tools that changed. Local-first.

MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.

Search, read and research the web, with hidden text stripped by default and sources hashed

Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.

Dead code, security, secrets detection and code quality for Python, TypeScript, Go.

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

Capability-aware MCP client for a Docker-hosted Kali Linux tools API

Drop-in MCP security middleware: audit · policy · human-approval · injection defense

VEXA MCP Server — security scanning via Model Context Protocol

Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.

MCP (Model Context Protocol) server for Vergate — run security scans, tech profiling, performance, SEO/AEO and accessibility checks from Claude Code, OpenClaw and other MCP clients.

Read-only pre-trade token risk verdicts and size-aware Solana exit screening for agents.

Security scanner for Model Context Protocol (MCP) servers

Security scanner for Model Context Protocol (MCP) servers

MCP server for Unplug — LLM defense layer for Claude Code, Cursor, and more

Probe an MCP server for input it should refuse. Connects as a client, inventories the tools, and reports what was accepted.

Deterministic MCP Security Architecture. FrozenNamespace as Root of Trust for Model Context Protocol tool verification.