- Securityscan @securityscan-api/securityscanSecurity for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Mail @honeycrisp-suite/mailApple Mail over MCP: fenced reads, draft-only writing, human-gated actions, audited with undo.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Bolyra MCP @bolyra/mcpMCP auth middleware: gate tool calls so only authorized agents can act.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Gateway @authzx/mcp-gatewayAuthzX MCP Gateway — policy-enforcing proxy between AI agents and MCP servers9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Logi Approval @1pass/logi-approvallogi Agent Approval Gate — human approval on the phone before high-risk agent actions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Stale Gate Janitor @usedailyai/stale-gate-janitorDaily 04:00 CT housekeeping over data/approval-gates/14% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- GVNR by Instruxi @gvnr/enforcer-governorGVNR (gvnr.io): stops AI agents overspending and running dangerous commands before they act.Not assessed yet.Runs on your machine, installed from npm.
- Kineti @therawlogs/kinetiKineti: spend cap, undo, and test proof for AI coding agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 402-LAB @kairose-master/402-labBudget-capped x402 buyer: delegate USDC in plain words, agent discovers and pays per call.13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Continuity Evidence @zerohourzulu/continuity-evidenceA bounded local evidence tool with current agent permission checks and durable retry handling.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Sovereign Identity Wallet @tamtunnel/si-wallet-mcpSelf-hosted signing wallet: DIDs, agency grants, and task mandates for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentGuard @merchantguard/agentguardLocal spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Verimand MCP Authority Server @verimand/mcp-authority-serverAgent-native access to verifiable VAGP authority.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AXIOM @dragoscv/axiomTransactional write gate for coding agents: plan, canonical manifest, checks, two-phase apply.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nofax @akzar1el/nofaxHuman-in-the-loop approvals and notifications for AI coding agents through a local stdio MCP server.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Once @stringsofthemind-oss/onceDeveloper assessment/setup MCP; admitted Once boundaries protect writes, not sibling connectors.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AETRE & The Governed Agent @grayclayton/aetre-mcpDecision-theoretic triage and fail-closed agent gating: 32 tools over stdio.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.
- Ratchet @iversonwuwei/ratchetRead-only tools to inspect your agent setup: list MCP servers, flag unpinned ones, test a policy.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- vaultguard @ashishrao-4/vaultguardAI agents use your Obsidian secrets by name — values never reach their context.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- VERAX @verax-ai/veraxThe body an agent asks before it acts: decide, approve, and keep a signed record on your machine.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- VPS Guardian @murzirius/vps-guardian-mcpSecure SSH bridge for AI agents to observe and safely administer Linux VPSs.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Lex @smartergpt/lexEpisodic memory, Frames, Policy Neighborhoods, and policy enforcement for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PitBridge @pitbridge/pitbridgeLocal-first MCP bridge for NinjaTrader 8 behind a deterministic guardrail engine.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Mandate Verification @api-disk-integrations/agent-mandateVerify a proposed action against a signed Agent Mandate without executing or mutating accounts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
