- 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.
- 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.
- 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.
- Agent Guard @ipezygj/agent-guardSafety checks an agent runs before it acts: package malware, destructive command, secret leak.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- CPFS @jonahalexanian/cpfs-mcpCPFS Runner as an MCP server — deterministic AI coding guardrails via a compiled WASM core.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- SENTINEL @teodorofodocrispin-cmyk/sentinel-mcpPre-execution safety oracle for AI agents. Screens Base contracts, simulates sells, pays via x402.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Signato @signato-ai/signatoLocal confidentiality chamber: blocks the wrong AI output before it leaves the machine.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Paysafe @paysafe-agent/paysafePayment firewall for x402: scans for replay, overpayment, PII/secret leaks, prompt-injection.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Positif @positif/positifThe agent switchboard: identity, policy, loop-guard, and an append-only audit ledger.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Gate @forgeorbital/agent-gateLocal mandate gate and proof trail for AI agents that take consequential actions.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Atomadic Nexus @atomadic/atomadic-nexusAtomadic Nexus — trust layer for the agent economy. 32 tools: trust gates, x402, lineage, swarm.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Think @agentutil/think-mcpIntent security pre-flight checks for autonomous AI agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mgc Blackbox @zkeviny/mgc-blackboxA trusted local encrypted execution boundary for AI agents.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Bash Vet @temurkhan13/bash-vet-mcpVet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- QAE Safety Certification @tb8412/qae-safety-mcpDeterministic pre-execution safety certification for autonomous AI agents.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Tool Filter MCP @respawn-app/tool-filter-mcpMCP proxy server that filters tools from upstream MCP servers via regex-based deny list6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nogra @nograai/nogra-mcpVerify-before-done trust layer for AI-assisted work. 32 tools, local-first, no credentials.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Guardrails @logi-cmd/agent-guardrailsMerge gates and safety checks for AI coding agents via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Infraveil Agent Guard @infraveilhq/agent-guardGate an AI agent's destructive actions behind human approval, with a tamper-evident log.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Infraveil Control Plane @infraveilhq/control-planeGovern your backend control plane from your AI agent - signed, human-approval-gated.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Almega @almega-ai/almega-mcpThe immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Sudo @kisyntra/agent-sudo-mcpMCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ThornGuard @qwady/thornguardRemote MCP security gateway for auth, redaction, policy enforcement, and audit logging.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
