The real catalog of tools for AI agents

Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).

Trust verification for MCP servers. Check scores, scan for security issues, search 4,200+ servers.

Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.

ToolGuard paid gate decisions and attestation lookup. Customer API key required. Limited beta.

Local guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning

Security scanner for MCP servers. SSRF, path traversal, injection, auth, secrets. Grade A-F.

Search the tool catalog. Customer API key required. Catalog metadata is not a security guarantee.

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

Check proposed actions against existing policies. Never executes actions. Customer key required.

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

Check existing content grants and expiry. No content fetching. Customer key required.

FX protection for SMEs — price Guards, live spot/forward rates, settlement dates, and more.

Persist failure simulations. No external fault injection or transfers. Customer key required.

Safety execution proxy protecting clients during tool calls.

Read-only XRP Ledger token-risk, issuer-authenticity and wallet-security checks.

Compute explicit durations. No reminders or legal guarantees. Customer key required.

Post-quantum cryptographic library protecting data packets.

Read unfunded contract drafts. No deposits, payouts or settlement. Customer key required.

Read public model catalog metadata with freshness timestamps. No model execution or payments.

Deterministic authorization and security guard for AI agent actions with signed receipts.