- Verify Claim @sudo-ai-git/mcp-verify-claimForce evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Residue Evidence @fantasyce/agent-residue-evidenceReport local task-scoped test and build residue without cleaning resources.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- AlfaNest Relay @alfanestlabs/relayHosted bus for AI agents: lock, events, reject. Publish/apply stay on the sidecar.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- FlightSweeper @flightsweeper-webmcp/publicAnonymous public tools for FlightSweeper. See the published agent boundary before use.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Safe4 @safe4/safe4Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- pgops @arzharch/pgops-mcpSafe, audited PostgreSQL operations for AI agents: queries, migrations, EXPLAIN, containers3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- XGuard — Agent Execution Gateway @moelayyan90/xguard-control-planeScoped agent execution. Server-side credentials, policy, budgets and verifiable receipts.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Seal @aurumflux20/sealStops agents double-charging across processes: exactly one execution, confirmed by the provider.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Blackwall X402 Guardrail @blackwalltier/blackwall-x402-guardrailKeyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SafeSelect MCP @antonillos/safeselectFail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Sovereign Gateway @mattijsmoens/sovereign-mcp-gatewayGating proxy for MCP servers: policy, verification and one audit trail across upstreams.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Copilot Datagate @afurlane/copilot-datagatePolicy-driven, read-only MCP server for safe database access from AI tools.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Bristlecone Logic @bristlecone2026/bristlecone-logicMicro-settled web content extraction and JSON schema validation utilities for AI agents via XRPL.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Conductor @icohangar-ops/agent-conductorAGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Chp @icohangar-ops/chp-mcpSpend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Subagent MCP @thang1710/subagent-mcpLet Codex orchestrate external coding agents through their native harnesses.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- obsify @formative-sum41/obsifyLocal, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Moltline Agent Governance @moltlinestudio/governAudit MCP configs and skill files for over-broad scope and injection risk. 6 of 8 free.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Grok Build @nuruvala/grok-build-mcp-serverRun the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- GateCore Marketplace @gatecoreai/marketplaceProcure governed AI capabilities: machine-readable price, scope, trust, gateway-delegation terms.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Janus @tonylchang/janus-mcpSecure Kubernetes MCP server: scoped, redacted diagnostics and human-approved writes6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Action Gate @aah20/agent-action-gateGate/Prove: deny unattended destructive agent tools. Instant Audit $499 on a2zsoc.com.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- XGuard — Payment Decision & Discovery @moelayyan90/xguardPayment decisions, durable evidence, x402 resource discovery and live gateway status for AI agents.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- shopify-operations-mcp @jpka/shopify-operations-mcpSafe-write Shopify operations: plan-before-execute writes with out-of-band approval and audit.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
