"Information about guardrails" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
Ask about your Yungle transfers, share big files, download what you're sent. Approve every send.
Scans text for personally identifiable information — emails, phone numbers, SSNs, credit card numbers, physical addresses, names — and returns a redacted version. Built for agents sanitizing user content, support tickets, logs, or documents before storage, sharing, or feeding into another LLM call. Pay-per-call via x402 (USDC on Base): $0.01/call, no account or API key. tools/list and /openapi.json are free for discovery.
Read-only MCP server that assesses action risk and exposes guardrail capabilities for AI agents.
Read-only MCP server that answers questions about turva.dev from its published data. Five tools return JSON: the service catalog with prices, contact and operator details, engagement principles and dated agent-readiness and security evidence with verification links. Connect over Streamable HTTP. You need no API key. The server does not scan other websites or run audits.
Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.
Query WHOIS/RDAP information for domains, IP addresses, CIDR prefixes and ASNs. Self-hostable.
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
Canadian public-sector data and legal information for AI agents, paid per call in USDC over x402
A free, deterministic self-check that returns an indicative Agent Risk Rating from user-provided answers about an AI agent's controls.
Ask questions about your login security data: risk scores, blocked logins, Tor, VPN and bot traffic.
Verification layer for the agentic web: a signed answer about any site before an agent acts.
Local checks for sudo, systemd, sshd, ufw, and secret leaks before an agent applies them.
Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.
Pre-signature x402 payment-risk oracle. AI agents call forecast_payment before paying a counterparty and get a GO / HOLD / STOP verdict from settlement reputation, price-anomaly (quoted vs the payee's own median), and OFAC sanctions screening — plus a third-party-verifiable Ed25519 signed receipt. Verdict only; never takes custody. Free under $10 at risk; returns an x402 payment challenge over that.
Verify artifacts, hand off public state, and record, check and find evidence about capabilities.
Screen a name against the U.S. Treasury OFAC SDN list. Information, not a compliance determination.
Jailbreak-proof AI guardrails. Automated Reasoning SMT solver, not an LLM. ZK proofs included.
Cloudflare Workers MCP server: ai-guardrails
Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation
Email for AI agents, with guardrails. The Notix MCP server lets an agent send and manage email through the Notix API using scoped keys: sandbox keys for safe testing, live keys that require approval before big sends and enforce daily caps. Also covers OTP/verification codes by email and SMS.
LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails
The internet's largest queryable infrastructure graph — 7.39 billion nodes, 39 billion edges, 5.6 million threat-intelligence relationships. Pivot from any IP, domain, or ASN across DNS, BGP, WHOIS, GeoIP, and threat intel in a single Cypher query. Most threat-intel and OSINT APIs are point lookups: you ask about one indicator, you get one record. Investigations don't work that way — you start from one suspicious domain and need to trace its hosting, its sibling domains, its registrar, its email
Connecting AI Agents to tools and data via the Civic MCP Gateway gives builders access to guardrails, scoped permissions, audit trails, and revocable access when calling MCP tools. Civic separates the permission layer from the AI agent so they can't get around restrictions.
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Permission-aware onboarding MCP server: answers about a codebase, filtered by the caller's role.
Ask about your customers' Azure costs, compliance and Microsoft 365 security.
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
Read selected digital-legacy matters and check missing information. OAuth and item consent required.
