- PolicyVault @zapsoblige-hash/policyvaultNon-custodial Kaspa policy enforcement for AI agents; signers retain custody.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Phases Agents @cherridsaid/phases-agentsDeterministic skill selection: local discovery, strict validation, every skill classified.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Enterprise Gateway @benjaminj/enterprise-mcp-gatewayProduction-grade MCP Gateway in Go with RBAC, in-flight PII redaction, and audit logging.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Trazum @davmunrey/trazumTrazum as an MCP server: let an agent price and budget its own prompts before it sends them.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Cedulon @dogrucanemek-alt/cedulonPolicy-gated agent spend with signed receipts and rail-extract audit6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- InterAI Risk Oracle @interailabs/ai-risk-oraclePre-execution policy gate for consequential agent actions with durable trust receipts.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Azure DevOps @dockndevai/mcp-azure-devopsAzure DevOps boards, repos, pipelines & projects for AI agents — governed.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- OrchestrUI @ecd5a/orchestruiDeterministic UI policy, discovery and audits for coding agents across seven ecosystems.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- LRSI @anamized/lrsiLocal recursive self-improvement OS MCP with fail-closed governance and gated mutation tools.20% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- OpenMesha @anamized/openmeshaOpen agentic operations mesh MCP: agents, workflows, cost, governance, and x402.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- SealGate MCP Gateway @sealgate/gatewayMCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- ThoughtProof @thoughtproof/thoughtproof-mcpPre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- 404.directory @mm-sheng/404-directoryRisk preflight for AI Agent tool actions and Polymarket settlement and execution checks.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Policy Gate @3labsio/policy-gateDeterministic allow/require_approval/deny verdicts for agent actions, before they happen.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Elicitly @elicitly/elicitlyHuman-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Gatewerk @gatewerk/mcpThe open-source review layer for AI agents. Work done for humans is decided by humans.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Shield KYA @the-pixel-boys/shield-kyaKYA MCP gate: evaluate, ingest, request approval. Sole PEP is Shield.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Agentic Wallet Guardian V3 @rudimentall1/agentic-wallet-guardian-v3Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Scripthold @zoster81/scriptholdSecure encoding-aware local workspace runtime for AI agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- AgentTakt @ryoohshima/agenttaktReview, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Agent Guardrail @rudimentall1/agent-guardrailDeterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- koment @koment-dev/komentRead and write checked code rationale stored outside source comments.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- ArkHive MCP @sammyboi81/arkhiveTamper-evident memory + governance MCP for Claude Code, Cursor, Codex. Ships the Seatbelt kit.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- DCL Trust Oracle — AI/LLM Output Audit (x402 MCP) @fronesislabs/dcl-trust-oracleAI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
