- Desk by Ouroboros Apps @lahutchins91/deskCustomer support answers, refund rules, and escalation limits for AI assistants5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Scope by Ouroboros Apps @lahutchins91/scopeFreelance scope of work, rates, deadlines, and change orders for AI assistants5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Proving Ground @railway/proving-groundAccounts-payable exception environment with a pass/fail verifier and proof packet: AI agents work AP9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Remit language tools @mrpacstar2-oss/remitChecked language for AI-written agent workflows: limits, cost and data flows known before running.Not assessed yet.A remote server; no sign-in.
- ExactGround @alidaram99/exactgroundCheck npm/PyPI packages exist and that a function or method exists in an exact package version.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Prior @bret1976/priorSpend gate agents call before money moves. Buy with Stripe Checkout. Paid only when Stripe says so.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Lumière PayCheck @book0feli/paycheckCheck any x402 endpoint before your AI agent pays it: trust grade, verdict, and hijack checks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Pink Agentic AI Payments (sandbox) @pinkwallet/agentic-payments-sandboxApproval layer for AI agent payments: budgets, rules, human approval. Sandbox, test credentials.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Lawang Onboard @gablooge/lawang-onboardPermission-aware onboarding MCP server: answers about a codebase, filtered by the caller's role.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- MarketNow @alicelabs-llc/marketnowVerify agent credentials, 9 formats, scam domains; search 70k+ MCP servers with auth-gate state.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TWZRD Agent Intelligence @twzrd/twzrd-agent-intelPre-spend trust for AI agents that buy: check x402 services and product listings before paying.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Covenant @jdhart81/agent-covenantDeny-by-default authority leases for agents wielding real power.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Hive Orchestrator @jdhart81/agent-hive-orchestratorDeterministic nested hive-mind orchestration over the A2A rails: hire N solvers, adversarial cross-r8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- agentguard — policy proxy for agent tool calls @agentwares/agentguard-cloudFree spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Solana Pulse: agent safety layer @timothymycompc/solana-pulse-gatewayStops AI agents losing money on Solana: pre-sign checks, intent matching, token verdicts. x402 USDC.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AGTS MCP Server @obligationsign-io/agts-mcpSovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act and SOC 2 ready.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- X402 Payment Safety @agenttanuki/x402-payment-safetyAuthorize x402 payments before signing with request-bound, signed safety decisions.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Perception @geiant/mcp-perceptionGeospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Acp @agenticcontrolplane/acp-mcp-serverSee, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- crosscheck @crosscheckapi/crosscheckChecks for AI agents over x402: review drafts, accept-check handoffs, scan skills before install.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Spelunking.ai @spelunking/hubStructure for hard AI decisions, and a human to escalate to when the structure runs out.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Overwing @overwing/mcpGuardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- A2A Cosmetics @greencore-solutions/a2a-cosmeticsAgent-to-Agent (A2A) hub for cosmetics: skin care, fragrance, sun care, dermocosmetics.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Veyra @zapxlabs/veyraGive AI agents a wallet with a spending limit. Non-custodial USDC on Base, server-enforced limits.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
