- Google Antigravity @turkeryakup/mcp-server-google-antigravityMCP server exposing Google Antigravity (agy CLI / Gemini): jobs, codebase analysis, file tools.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Wisepanel @ikoskela/wisepanel-mcpMulti-agent deliberation across Claude, Gemini, and Perplexity. Stream and publish.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Liquid @ertad-family/liquidConnect your AI agent to anything — APIs, databases, and agents; read and write, auto-discovered.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Zoogent @bepunk/zoogentAI agent orchestrator with Architect AI. Multi-team, web dashboard, 35+ MCP tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Azeth Protocol MCP @azeth-protocol/mcp-serverSmart accounts, x402 payments, on-chain reputation, and service discovery for AI agents9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Swarmwage @swarmwage/swarmwageHire and pay specialized AI agents in USDC on Base. Open MCP protocol above x402.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Oasyce @shangri-la-0428/oasyceOn-chain economy for AI agents: escrow, marketplace, data rights, reputation, disputes.13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Agent Audit @rumblingb/agent-audit-mcpImmutable audit trail for agent-to-agent interactions8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.3 GitHub stars.
- WAKE Protocol @omodaka9375/wakeA post-mortem succession protocol for AI agents. Black Box, handoff, time-locks.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Agentled MCP @agentled/mcp-serverIntelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Tower @rohanxmalik/towerMultiplayer for AI coding agents: collision detection before the edit, messaging, delegation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Noetive @noetive/mcp-serverYour agents share what they learn. Semantik finds it by meaning, with no topic names to agree on.Not assessed yet.Runs on your machine, installed from npm.2 GitHub stars.
- agent-mailbox — Mailbox and Wake System for AI Agent Teams @polaris-smart/agent-mailboxMailbox + wake system for AI agent teams: letters always land, right agent wakes, quiet otherwise.Not assessed yet.Runs on your machine, installed from PyPI.2 GitHub stars.
- Lokal @slookisen/lokal-mcpNorwegian local-food MCP: 1,431+ farms, shops, markets + umbrellas (Bondens marked, Hanen, REKO).3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- omp-worker-mcp @divenire990/omp-worker-mcpDelegate complete coding tasks to the local OMP default model and inspect the result.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Dibs @agenxy/dibsTells an AI agent when another is already doing its work. Board, typed mail, directory claims.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- Model Council @totti0135/model-councilConsult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Pipe (SPR) MCP Server @machuraharry/pipeAI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- AIShield Security Scanner @lm203688/aishieldScans MCP servers for tool poisoning, prompt injection and supply chain risks.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.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.
- Concord @zkwasm/concord-mcpMulti-agent collaboration rooms with E2EE and server-enforced coordination primitives.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- The402ai MCP @the402ai/mcp-serverAI agent service marketplace — browse, purchase, and manage services via x402/USDC11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Synapbus @synapbus/synapbusMCP-native agent-to-agent messaging hub with channels, DMs, and semantic search6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- BasedAgents @maxfain/basedagentsMCP server for BasedAgents, the task marketplace for AI agents: claim paid tasks, get paid in USDC.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
