- Pkgtruth @hxckya/pkgtruthCatches hallucinated and slopsquatted npm and PyPI packages before an agent installs them.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- ReviewGuard @eclipsesource/review-guardSafety boundary for agent written GitHub PR reviews: pending and invisible, submitting is opt-in3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Lossless Context @northtekdevs/lossless-context-mcpAgent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- ComplyEdge TrustLint — offline EU AI Act compliance checks @complyedge/complyedgeOffline TrustLint checks: EU AI Act Article 5, Article 50, GPAI, plus GDPR and HIPAA.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- q-ring @i4ctime/q-ringOS keychain secrets for AI coding agents, over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Last EHR — Medplum @cbetz/last-ehrFHIR chart tools for MCP: read-only by default, with elicitation-gated, human-approved writes.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Hivelore @doucs91/hiveloreDeterministic gate: blocks any commit whose diff reintroduces a documented team mistake.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Release Gate @vamsisudhakaran1/release-gatePre-deploy security auditor for AI agent code — the risks generic SAST misses.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- mcp-audit @saagpatel/mcp-auditScan, enumerate, and risk-score every MCP server configured on your machine.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Guardian @rudraneel93/mcp-guardianSecurity, cost, and health governance proxy for MCP infrastructure6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Nervous System @levelsofself/nervous-systemGovernance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Agence @l-agence/agenceAI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Veto @jigyasudham/veto93 agentic MCP tools + 49 specialist agents for every major AI CLI. Self-learning, no API keys.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Nexus @j7an/nexus-mcpDelegate tasks to coding agents (Claude, Codex, Antigravity) from any MCP client9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Aguara MCP @garagon/mcp-aguaraScan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.4 GitHub stars.
- Jira Scoped @deepwired/mcp-jira-scopedJira MCP server with scoped API tokens via api.atlassian.com gateway3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Projscan @abhiyoheswaran1/projscanAgent-first MCP. 11 AST adapters, 12 named languages, 51 tools, mission outcomes. Local.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Korg Introspect @new1direction/korg-introspect-mcpWrap any korg:introspect@v1-aware binary as a Claude Code tool, honoring declared side-effects.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Lore Context @lore-context/lore-context-mcpGoverned AI-agent memory, Evidence Ledger traces, evals, and portable context tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Termada @islomzoda/termadaPersistent, policy-controlled missions for AI agents operating local and SSH environments.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.4 GitHub stars.
- Haldir @exposureguard/haldirGuardian layer for AI agents: identity, secrets, audit via MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Tanilo @tkcollective/tanilo-mcpTanilo checks the premise before an AI agent acts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- mcp-pin @gautamtalksdev/mcp-pinCheck if an MCP server's tool definitions changed after approval, from a signed public log.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Ramen: self-hosted MCP for teams @bkraad47/ramenMulti-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.3 GitHub stars.
