Search

MCP server that audits agent/MCP source for OWASP MCP10:2025 context oversharing — unrestricted session/memory dumps, cross-user shared context, system-prompt leakage via tools, and unscoped vector recalls

MCP server that builds a reachability graph across multi-agent orchestration configs (LangGraph, CrewAI, AutoGen/ag2) to find transitive excessive agency — an agent with no dangerous tool of its own that can still reach one through delegation or group mem

MCP server and reverse proxy that catches leaked credentials and PII (API keys, TC Kimlik No, credit cards, IBANs) in outbound LLM prompts before they leave your application

PII masking and prompt injection detection library: checksum-validated Turkish and international identifiers, KVKK special categories, secrets, and lethal-trifecta tool classification

Drop-in deterministic policy layer for MCP-using AI agents

Shared opt-out usage telemetry client for GuardBee MCP servers

Search US vehicle listings from dealer sites, with price stats, VIN lookup, and dealer profiles.

WAFtester — the most comprehensive WAF testing CLI & MCP server

LangChain integration for SafePrompt — prompt-injection detection as a callback handler. Validates every prompt flowing through a chain before it reaches the LLM.

The MCP bridge that audits your routes before exposing them to LLMs — and blocks prompt-injection at runtime.

MCP server that audits installed MCP client configs (Cursor, Claude Desktop, Windsurf, VS Code) for unpinned packages, secrets in env/args, wildcard auto-approve, unauthenticated remote endpoints, typosquats, and cross-server tool shadowing

Temporary package placeholder for staged publishing

OWASP-inspired launch gate for AI agents — scan MCP configs, test policies, simulate risk, and generate compliance evidence. Static-only, offline, no API keys.

Offensive MCP server auditor — detects tool poisoning, credential leaks, RCE vectors, SSRF, session hijacking, and supply chain vulnerabilities across stdio, HTTP, and SSE transports.

MCP server that probes vector-database endpoints (Weaviate, Qdrant, Chroma, Elasticsearch/OpenSearch, Redis, Postgres/pgvector) for unauthenticated exposure of embeddings and RAG data

MCP server that audits MCP server source for OWASP MCP08:2025 (Lack of Audit and Telemetry) — missing tool-call logging, raw args/results in logs, disabled audit sinks, and tool errors swallowed without a record

Offline scanners for the code patterns behind 53 CVEs in 9 AI-agent frameworks, plus MCP tool pinning. No dependencies, no telemetry.

GuardBee MCP bridge to Agent Threat Rules (ATR) — evaluate agent/MCP events against the open Sigma-like detection standard for prompt injection, tool poisoning, context exfiltration, and MCP attacks

MCP server that scans MCP server code for elicitation anti-patterns in the 2026-07-28 spec: form mode asking for secrets, URL mode pointed straight at a third-party authorize endpoint, and credentials or PII embedded in the elicitation URL

MCP server for Workforce AI — policy management, asset visibility, and apps catalog via LLM tool calls