- Intent-Verified Development (IVD) @leocelis/ivd33 tools that make AI write, implement, and verify intent against explicit, testable constraints.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- K-Work Trust @hycore220/k-work-trustKorean business record validation and workflow safety gates for AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Shadowgate @josephibra/shadowgate-mcpSecurity firewall for AI agents — scans MCP calls for injection, secrets, and risks.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Mission — Trust Graduation Gate @gomission/mcpTrust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Second Eyes Agent Workflow Services @this-is-hellgate/secondeye-mcp-unblockWorkflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.31% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Catalyst Governance @stratogenic-ai/catalystGovernance middleware for AI agents: permission gates, approvals, compliance scanning, audit ledger.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- A2a Governance Bridge @csoai-org/a2a-governance-bridge-mcpA2a Governance Bridge MCP Server by MEOK AI Labs14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- DepScope @depscope/mcpPackage intelligence MCP for AI agents — 22 tools, 19 ecosystems, AGPL SDK, free.28% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Gvnr @gvnr/gvnrBudget & cost control for AI agents — per-agent spend caps + rate limits before each call.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- AGTS MCP Server @obligationsign/agts-mcpSovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act ready.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Shield @craftedtrust/mcp-shieldTrust verification for MCP servers. Check scores, scan for security issues, search 4,200+ servers.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentcore @geiant/mcp-agentcoreAI governance MCP server for EU AI Act compliance and jurisdiction verification8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Invinoveritas @babyblueviper/invinoveritasSecond opinion before an irreversible agent action; signed proofs, free verify, public ledger.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- A2aidentitytoll @clauxel/a2aidentitytoll-mcpRemote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Agentdataboundary @clauxel/agentdataboundary-mcpPermission boundary receipts for ChatGPT agents.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Taste @humantaste/taste-mcpExpert review for AI agents. On-chain proof of human review.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Rail Score @responsibleailabs/rail-scoreResponsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Rightshold @rightshold/rightsholdKnow what your agent may use: license checks, entitlements you hold, signed rights manifests.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Eligibility @pythonanywhere/agent-eligibilityDeterministic eligibility scoring for AI agents: CLEAR/HOLD/FAIL verdicts, published weights.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Investboard @investboard/investboardInvestment rules and decision history for AI assistants: read your policy, check changes, review.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Harbor (gethrbr) @gethrbr/harborTeam memory for coding agents: rules you approve, served to every agent, and which ones it cited.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ActionBox Human Input @actionbox/human-inputHuman review for AI agents: ask through ActionBox and retrieve a typed decision before proceeding.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Acutis Gate @acutisgo/gateEvery AI tool call runs as the person who asked, under your rules, fully audited.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Vicem @vicem/vicemSee the calls your Vicem answered and ask it to call or message someone, with your OK first.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
