- kcp-harness — KCP compliance proxy @cantara/kcp-harnessMCP compliance proxy between agent and tools: deterministic governance, fail-closed, audit trail.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Authoryze @authoryze/authoryzeGive your AI agent a spending limit: approval controls and single-use virtual cards.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- 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.
- PLwC - Personality Layer with Conscience @mhoedt-ai/plwc-gatewayGoverned local MCP gateway for workspace, sandbox, document and profile operations.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Agent Hub @blackaxgit/agent-mcp-hubOne MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MCP Blast-Radius Auditor @aos-standard/mcp-blast-radiusStatic blast-radius audit for MCP servers before agent install. Manifest optional.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ALEETH Authority MCP @aleeth/authority-mcpThe first MCP governed by ICA. Every action is gated and sealed with a verifiable receipt.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- AI Guardian @aiops-tools/ai-guardianGoverned local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- SQL MCP Server @nethinwei/sql-mcp-serverControlled SQL access gateway with policy, cost limits, tenant isolation, and safe tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Tctc @kofujimura/tctc-mcpERC-7303 token-controlled roles for AI agents: grant, check, and revoke permissions on-chain5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Palveron Governance Gateway @palveron/governance-gatewayAdvisory governance checks for MCP hosts; enforcement runs in the Palveron remote MCP proxy.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Sentinel Payment Boundary Tools @terminallylazy/sentinel-recovery-servicesRead-only payment-boundary preflights plus an unsubmitted public quote-request draft tool.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Stillos Kya @stillmarcus24/stillos-kyaCounterparty due-diligence infrastructure: OFAC screening, on-chain risk, signed verdicts.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Keel @tdalbanmoreynas/keelCatches your AI coding agent when it games the tests - locked-test hashes, tamper detection.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Gatekeeper @runestone-labs/gatekeeperRun MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- sql-steward @pawansingh3889/sql-stewardThe agent never writes SQL: queries compile from a semantic layer you control, PII refused first.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Transaction Control @flint/agent-transaction-controlIssue Agent Passports and verify agent authority before value moves. Signed verification records.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MCP Server Attestation @studiomeyer/server-attestationEd25519-signed MCP tool manifests + spawn attestation. Layer-2 supply-chain hardening.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- SWT3 AI Witness @tenova/swt3-witnessCryptographic AI governance and audit. 75 tools, 84 frameworks. EU AI Act, NIST, CMMC, MCP Top 10.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Brand Voice @zoharbabin/brand-voiceEnforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- L402 Gate @zekebuilds-lab/mcp-l402-gateL402 Lightning paywall + DoI score gate for MCP tools: challenge, verify, score.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- wa — safe WhatsApp automation @yolo-labz/waSafety-first WhatsApp tools: draft-gated sends, enforced rate limits, append-only audit.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- SignalBrain @whitestone1121-web/signalbrainVerifiable receipts for governed process changes; emit, validate, and gate trust6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- WithVibe Voter @withvibe/withvibe-voterVote-gated change control for WithVibe — the agent proposes a change via MCP; team approves first.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
