- Agentshield @dl-eigenart/agentshield-mcpDetect prompt injection, jailbreak, and social-engineering attacks in LLM agents.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Envibe @dominic-righthere/envibeSecure permission layer between AI agents and your .env files4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Immune @denial-web/agent-immuneAI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Over-Reach Detector @choreoatlas/over-reach-detectorDetect when AI code changes exceed declared task scope (MCP server).3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Heimdall @caglarbozkurt/heimdallScan an MCP server or agent config for injection, exfiltration, and risky capabilities.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Gateway @bolyra/gatewayMCP auth gateway: verify agent identity, enforce per-tool permissions, block replays, emit receipts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Clawvault @andrewszk/clawvault-mcp-serverAI agent payment security - spending limits, whitelists, and human approval.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentIAM @achilliesbot/agentiam-mcpStdio MCP wrapper for AgentIAM's 18 x402 endpoints — agent safety + intelligence on Base.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Zentric Protocol @zentricprotocol/zentric-protocol-mcpPrompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Proof Layer @world-999-labs/proof-layerSigned, hash-chained provenance receipts for AI agent actions.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mund — MCP Security Scanner @tyox-all/mundScan for prompt injection, secrets, PII, and vet MCP servers before installation15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Safehold @spacetime-technology/safeholdLocal, encrypted MCP vault for passports, IDs, visas and photos. You control access.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Constraints Registry @sureshkhemka/constraints-registryPolicy-as-code guardrails for AI coding agents, validated via OPA, Conftest, Checkov & Semgrep.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Vectordecisions @nikitadatar/vectordecisions-mcp-serverAI Governance MCP Server - GATRI trust scoring, kill-switch, EU AI Act compliance for Claude5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Guardrail MCP Server @jarvisonm4/agent-guardrailAction-level governance for AI agents -- control what they DO, not what they SAY7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- CheckMCP @h129hj/checkmcpAudit any MCP server's security & quality — OWASP MCP Top 10 + explainable 0-100 MCP Score5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- mcp-crewd-rs @dionanos/mcp-crewd-rsCell fabric daemon: spawn and coordinate Claude/Codex/pi worker cells over MCP. Audited.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Sports Context Protocol @dswane/sports-context-protocolSelf-learning operational context layer for AI sports agents. Profile 001: golf.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Creedspace @creed-space/creedspace-mcp-serverConstitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MEOK Governance Engine @csoai-org/meok-governance-engine-mcpGovernance Engine MCP Server by MEOK AI Labs12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Firmware Attestation @csoai-org/firmware-attestation-mcpFirmware Attestation MCP — hardware trust layer for sovereign AI. Scan firmware, check17% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Veridion Nexus @brano80/veridion-nexusVeridion Nexus MCP server - GDPR Art. 44-49 runtime compliance for AI agents11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Blast Scope @atharva-jayappa/blast-scopeContextual blast-radius scoring for shell commands an AI agent is about to run3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- AI Firewall MCP @akhilucky/ai-firewall-mcpMulti-agent LLM security layer detecting prompt injection and jailbreaks.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
