- 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.
- 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.
- 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.4% 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-kyaAudit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.7% 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.
- koment @janpuc/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.
- Ownership Attestation Protocol @bg4ff8mtdn-dotcom/ownership-attestation-protocolMCP protocol enforcing explicit task acceptance and attestation-tagged completion claims.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- AgentEnvelope @blackboxengineering/agent-envelope-mcpNeutral MCP server for AgentEnvelope authority: sovereign verify + vault verify/lookup/mint.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Yagami AI Context Firewall @matthewtracy/yagamiOpen-source AI context firewall for governed model, retrieval, memory, and tool access.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- MCP File Tools @zoster81/mcp-file-toolsSecure encoding-aware filesystem tools with atomic writes, legacy encodings, and typed errors5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- Laguarde @futur-panda/laguardeSelf-hostable policy control plane for AI coding agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- ellmos ControlCenter @ellmos-ai/ellmos-controlcenter-mcpMCP control plane: local server discovery, profiles, capability bundles, and policy audits.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Willitsend @abryfs/willitsendDeterministic pre-send lint for SMS/iMessage: silent carrier filtering and segment blowups.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- mcp-gatehouse @nickgeorgeseo/gatehousePermission tiers, approval gates, and audit logging for MCP servers - the server is the gatekeeper4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Agentic SDLC MCP @sakuracianna/agentic-sdlc-mcpAgentic SDLC governance and security controls for AI coding agents working with GitHub.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Valta @billionaire664/valta-mcpFinancial governance for AI agents — spend gates and audit trail exposed as MCP tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- QueryPilot @nickklos10/querypilotSafe SQL gateway for AI agents: SELECT-only validation, access policies, masking, audit trail, evals4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
