"How to create draft emails using Gmail's support agent class" matching MCP connectors:

AI reasoning checks any document against known international standards before your agent acts on it.

Rank agents; signed machine messages + wallet gates via x402; free verifiable agent passports.

Hosted, OAuth-gated endpoint for quantakrypto's post-quantum crypto tools: scan code for quantum-vulnerable cryptography (RSA/ECDH/ECDSA/DH) and get NIST ML-KEM/ML-DSA/SLH-DSA migration guidance over authenticated HTTP — nothing to install. Sign-in required (Google/GitHub/email). Same tools as the open-source @quantakrypto/mcp server; source at github.com/quantakrypto/pqc-tools.

Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.

Runtime permission, approval, and audit layer for AI agent tool execution.

Governance firewall for autonomous AI agents. Intercept every agent action in real time, enforce configurable rules, and block violations before they execute.

The PropelAuth Integration MCP Server helps you and your favorite AI agent integrate PropelAuth as quickly and easily as possible into your project. Whether you're integrating PropelAuth into your Next.js project or your FastAPI backend, the Integration MCP Server will ensure your AI agent has the best context possible for a successful integration.

Confirms an AI agent/service is who it claims to be (domain + agent-card + MCP handshake).

Trusgent MCP — Trust Layer for AI agents. HK registry + Agent Cards. Default: get_merged_profile.

Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.

Audit MCP configs and skill files for over-broad scope and injection risk. 6 of 8 free.

Per-transaction crypto trade validator for AI agents. Returns deterministic PROCEED / CAUTION / BLOCK verdicts using WaveGuard anomaly detection, history checks, and rug-pull risk analysis.

Authorize x402 payments before signing with request-bound, signed safety decisions.

Read-only Remote MCP for externally grounded AI agent trust receipts.

Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.

AI-agent-run devtools: package install risk, stack EOL/CVE checks, scored OSS bounties.

MCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysis

Pre-action allow/deny for AI agents. 24 statutes, 13 jurisdictions: EU AI Act, GDPR, DPDP.

Inventory and audit your agent fleet over MCP: audit_mcp_config returns risk-ranked findings with a 0-100 posture score, scope_check ranks tool-manifest blast radius, audit_skill_file and injection_scan screen untrusted skill files and text, and inventory_report builds a governance inventory with risk tiers. All analysis is deterministic and local to the request.

Scan agent skills and MCP servers for malicious patterns before you load them