mariocandela/beelzebub
Honeypot framework for building decoy MCP tools that an agent would never use in normal work, to detect prompt injection and malicious agent behavior.
| Category | Security |
|---|---|
| Runs | cloud |
| Official | Community |
Source: punkpeye/awesome-mcp-servers · Licence: MIT. Listed in MCP servers. We list tools; we do not test, rate or endorse them.
Related
tunahanaliozturk/derbent
One local gate for Claude Code, Codex, Copilot CLI and Antigravity: allow, deny and ask rules over MCP and built-in tool calls, approvals from a…
fredyee/hallucc-mcp
Claim-level hallucination detection with sources, agent trajectory verification, risk gating for computer-use actions and prompt-injection defense.
ucsandman/DashClaw
Fail-closed approval layer for unattended agent runs: checks actions against org policy, requests human approval and logs every decision to a causal…
26zl/cybersec-toolkit
Install a large security toolset and discover and run it through an authorization-gated server for CTF, pentesting, bug bounty and DFIR.
AIops-tools/Compliance-AIops
Turn other AIops tools' audit trails into tamper-evident, hash-chained evidence bundles mapped to HIPAA, PCI-DSS, SOC 2 and GDPR. Offline and…
dtkmn/mcp-zap-server
Self-hosted OWASP ZAP integration with guided security scans, findings summaries and report generation.
felixpg13-glitch/spendshield
Payment guardrails for AI agents: spend caps, budget and approval gates, prompt-injection defense, an encrypted secret vault and an audit trail.
rudimentall1/agentic-wallet-guardian-v3
Self-hosted security layer that evaluates AI agents' proposed blockchain transactions and returns an explainable allow, warn or block decision.