- Switchboard @wkoverfield/switchboardOne firewall and password manager for all your AI coding agents' MCP servers and secrets.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Junto @vrllrv/junto-mcpThe payment protocol for people and agents. One MCP server, any payment rail.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Injection Detector @viridis-security/injection-detectorFormally-verified injection/exfiltration detector for AI agents (MCP-02).4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Faro @vedux98/faroVerify URLs, payees, and messages before acting: red/yellow/green trust verdicts for agents.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- TWZRD Agent Intelligence @twzrd-sol/twzrd-agent-intelPre-spend trust for AI agents that buy: check x402 services and product listings before paying.13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Kit @toreva/kitPolicy-checked Solana wallet actions with user-set limits, unsigned transactions, and receipts.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Gateway @titus-civic/mcp-gatewayIdentity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Payfetch @forum-labs/payfetchx402 paying-fetch client for AI agents. Spending caps, approval, receipts. Non-custodial.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Warden402 @sukrutkrdg/warden402-mcpPre-execution security for AI agents on Base: guard token/tx/address + per-agent spend firewall.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Conduct AI @sseshachala/conduct-cliList agents, trigger workflows, and enforce team AI policies with ConductGuard.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- HiveGate — Hive Civilization Agent Trust & Settlement @srotzin/hive-gateTrust & settlement for AI agents: DID, ZK reputation, audit, USDC/USDCx/USAD/ALEO. First DID free.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- HiveAttest @srotzin/hive-mcp-attestPre-action attestation perimeter for AI agents — 8 primitives, signed C18 receipt per call.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sigma Gate @spektre-labs/sigma-gateDeterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Humsana @sriramnatrajhen/humsana-mcpDetect developer stress, focus, fatigue from typing. Block dangerous commands when tired.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Smartpolicy @smartpolicy-protocol/smartpolicyRuntime authorization for AI agents and smart contracts via an immutable on-chain policy registry6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MindForge @sairam0424/mindforgeRead the MindForge engine over MCP: knowledge graph, project health, and audit log.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cycles — Budget Authority for AI Agents @runcycles/cycles-mcp-serverRuntime budget authority for AI agents — reserve, enforce, reconcile spend across providers4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MCP OpenClaw Extensions @romainsantoli-web/mcp-openclaw138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Gatewards @rtahabas/gatewardsDrop-in spend governance + cross-agent dedup proxy for AI agent fleets, with x402 settlement.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentSecurityLens MCP Security Trust Check @professor2k8/agent-security-lensMCP security trust-check for agents before installing MCPs, Skills or tools.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Guarded WhatsApp @peter-tnc-453/guarded-whatsapp-mcpSecurity gate for agent-driven WhatsApp: allowlist, secret scan, rate limit, audit log.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Guard @mdfifty50-boop/agent-guardConstitutional guardrails and loop detection for AI agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Security @mdfifty50-boop/agent-securitySecurity scanning and threat detection for AI agents9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- WhatsApp @meharajm/whatsapp-mcpWhatsApp MCP Server - Human-in-the-loop for AI agents via WhatsApp8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
