- bundlebox @blackswanalpha/bundleboxWhere the work is, packed before the agent reads: brief, symbol tables, findings, token bill.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- jevnav @dtduc-git/jevnavReplayable browser automation: Jev picks the element, a gate blocks risky actions, every run traces.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- TollWarden @tollwarden/tollwardenScreens x402 payments before settlement for injected payee addresses and sellers who never deliver.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Panel Review @truverif/panel-reviewGuardian agent for AI coding: four frontier models review risky diffs and commits before they ship.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.2 GitHub stars.
- my-pi @boxboxmari/my-piLocal-first MCP runtime for coding agents with safe workspace access, AST/LSP navigation, and Git.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- OpenCode MCP Bridge @manuotel/opencode-mcp-bridgeCoordinate and verify OpenCode workers over MCP Streamable HTTP.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
- EthersFlow — Trust Gate for AI Agents @ethersflow/ethersflowTrust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- SpendShield @felixpg13-glitch/spendshieldAuthorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Keel @lutfizp/keelControl plane MCP that dedups scanner output, rate-limits hosts, and runs non-destructive proofs.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Securedact MCP @giganteshji/securedact-mcpLocal-first privacy MCP server for sensitive AI workflows4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- mcp-audit @firatmio/mcp-audit-proxyTransparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- WhitePact @guruprasath-annadurai/whitepactAI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
- Cernion Energy Tools MCP @cernion/cernion-energy-toolsEnergy-domain MCP tools for Cernion context, evidence and guarded process preparation7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.2 GitHub stars.
- Cursor Chat Bridge @udah1/cursor-chat-bridgeDrive the Cursor agent from Telegram, Discord, or GitHub — with images and voice notes.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Kāhea @copyleftdev/kaheaDeterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- Gpp @mahabubul470/gppProject knowledge graph with history-checked belief staleness, changeset proposals, cost reporting5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.2 GitHub stars.
- Inspectrum @yannmenec/inspectrumReview coding-agent plans on demand with peer models, attributed findings, and a structured verdict.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Hermes Plant — Agent Commerce Assurance @jessegdotio/hermes-plantPreflight, approve, and prove consequential agent actions with signed evidence and x402 tools.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Actenon Kernel @actenon/kernelVerify consequential AI actions before they execute.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Agentic MCP @hugolsramos01-bit/mcp-agentic-serverLocal coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Quesen Deterministic Agent Decision Layer @shxnque/quesenDeterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Myrmex Hive @olafkfreund/myrmex-hiveZero-inbound-port MCP gateway for managing distributed edge servers over reverse SSH tunnels8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- Cogmem @writerslogic/cogmemA self-improving, verifiable memory layer for AI coding agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- IntentFence Agent Action Firewall @razel369/intentfenceFail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
