- x402Shield @x402shield/x402shieldPublic demo: evaluate AI-agent payment authorization and approval policy. No signing, no settlement.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Economic Trust @caoviedoc/agent-economic-trustOutcome-calibrated economic trust gate for autonomous agents.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- JevStation @jevstation/mcpTyped-question decisions from Jev: classify, moderate, route models and guard tool calls.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- LiveGraph @livegraph/livegraphLive, editable canvas of your agent hierarchy — watch, interrupt, and reroute runs mid-flight.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- 402shield @mitchsingh/402shieldx402 payment security and pre-execution transaction risk screening for autonomous AI agents.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- R/IV — Verify Claims, Citations & Agent Actions @duranivrobert-glitch/rivVerify claims, citations & agent actions. Free receipt trial; paid prices via live R/IV quotes.Not assessed yet.A remote server; no sign-in.
- Attestari @attestari-ai/attestariAttestari's verdict on an npm or PyPI package version, asked before an agent installs it.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- booklint @booklint/deskChecks an agent's trades, spend, bookings and offers against its owner's limits. Facts, not advice.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- neonloops @neonloops/neonloopsBuild, run and check agentic workflows from your AI client: approve steps, read tables, see runs.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- AstraNL Crossing @astranl/crossingLook before work, claim it, check a spend, mark the outcome. For agents sharing tasks. No key.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Causara Economic Control @mahadrehman239-del/causara-economic-controlEconomic exposure and control decisions for autonomous AI actions in Shadow Mode.Not assessed yet.A remote server; no sign-in.
- MCP Operation Risk @dnsreicht/mcp-operation-riskOperation-level risk guidance for consolidated MCP tools, including schema drift and retry signals.Not assessed yet.A remote server; no sign-in.
- Oryah Mail @infinihash/oryah-mailGoverned email for agents: Gmail, M365 and IMAP; per-mailbox permissions, send allowlist, audit log9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- naturali @naturali/naturaliConfigure AI agents, give them knowledge and tools, and read back every generation they run.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- FHI MCP Server Security Audit @fhi-llc-1118/fhi-x402-security-toolsFree payment guide and Base-USDC x402 MCP security, package, domain, and SEC tools.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AI Agents Pitstop @ai-agents-pitstop/pitstopHuman approvals, autonomy limits and a chained audit log for the AI agents of service firms.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Intended @intended-so/intendedIntended's authority layer as MCP tools: ALLOW/ESCALATE/DENY decisions with signed tokens.Not assessed yet.Runs on your machine, installed from npm.
- autobus — signed attestations for agents, $0.01 per call @ninefiveonefive/autobusSigned attestations for agents, $0.01/call via x402: URL witness, AI permission, tx finality, JWKS.Not assessed yet.A remote server; no sign-in.
- SECONDED @secondedoracle/seconded-mcpThe oracle for agents. Verify trades, tokens and messages before your agent acts.28% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- HANRIA agent mandate check @hanria/agent-mandate-checkCheck an agent action against its operator's mandate before acting: permit, deny or escalate.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Preflight Checks (x402) @josediegorobles/preflight-checksDeterministic pre-execution verification tools for AI agents with x402 USDC pay-per-call on BaseNot assessed yet.A remote server; no sign-in.
- Guardian @oraclestech/guardian-mcpRuntime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid).9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ZP Nexus @sistemasinovadores/zp-nexusSuas IAs nos computadores e projetos da empresa, com permissões, aprovações e auditoria.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Check @hanria/checkCheck a proposed agent action against operator's rules: permit, deny or escalate, with the clause.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
