- Kit Lite @randall-75d/kit-liteInstant x402 spend-cap pack for agents. get_quote then buy_intel_pack 5 USDC Base. No human.41% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Reserve Protocol Authorization Firewall @chatgpt/agent-transaction-firewallAdvisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Ava @getava/avaCoding agents run multi-leg cross-chain DeFi. Legs re-derived from your sentence before signing.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- vrsai @vrsai/mcpMachine-native capabilities with explicit contracts and machine-readable commerce.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Assurly MCP @assurly/mcp-serverPre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AegisAI @kadopi/aegis-aiPaid pre-execution risk verification for AI agents over MCP and x402.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Weft @letsweft/weftOne board for every AI you use: agents claim tasks and finish with proof you accept or return.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Grantor @chaingrantor/grantor-mcpWrap any MCP server with enforced, bounded, revocable permissions — grant, narrow, check, revoke.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cofferline @cofferline/treasuryTreasury and risk controls for agent wallets: policies, quotes, prediction-market orders.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- OneDroid Synapse @onedroid/synapseGoverned MCP gateway: one endpoint for your tools, with credential custody and audit log.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Mandateguard @ezequiellich44-cmd/mandateguardDeterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- StructureClerk @structureclerk/mcpAI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- InfraPulse @infrapulse/infrapulseAI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Execute ai-right-to-opt-out-gate-mcp @evozim/ai-right-to-opt-out-gate-mcpPremium agentic endpoint for ai-right-to-opt-out-gate-mcp.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Penholder @penholder/penholderPreventive human-approval write-gate for AI agents: writes commit only after a human approves.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Fullmakt @fullmakt/fullmaktCredential broker for AI agents: scoped, revocable API access with policy enforcement and audit.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Elicitly Pro @elicitly/proHuman-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ShareWatch @sharewatch/sharewatchGive Claude only the Google Drive files you choose. Every action logged.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Utility MCP @insivotron/agent-utility-mcpStop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- GHOSBC Safety Gate @misfitmediahouse/ghosbc-safety-gateAgent governance with A2A/Shopify/MCP trust audits, action screening, and decision UI.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- ScrubMyText + Agent Infrastructure @scrubmytext/tools49 deterministic tools for text integrity, agent control, and contextual quality evidence.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SpringRoll @springrolldev/springrollRegister, deploy, review, and govern internal applications built with coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MUJ428 Trust Layer — Bind Approved Intent to Verified Effect @wmujahid428-web/muj428-trust-layerPayment-rail-independent intent-to-effect integrity for consequential agent actions.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentFabric — Human-in-the-Loop Review & Approval @enzoduit/agentfabricHuman-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
