"Ways to have Claude play Minecraft" matching MCP connectors:
Matching Connector Tools:
Scan and fix email auth (SPF, DMARC, DKIM, MX, blacklists, expiry) + DNS checks. Validated fixes.
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.
MCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysis
Measure how AI assistants cite your brand. Returns measured data and ready-to-apply fixes.
Check if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen.
Deterministic gate for AI agents: ALLOW/DENY a step before it runs, sealed to a verifiable receipt.
Breach intelligence API: email search, domain monitoring, passwords and stealer logs.
Validate whether an IP address belongs to Bingbot. Remote MCP server exposing a validate_ip tool.
Validate whether an IP address belongs to PetalBot. Remote MCP server exposing a validate_ip tool.
Validate whether an IP address belongs to Applebot. Remote MCP server exposing a validate_ip tool.
Validate whether an IP address belongs to Googlebot. Remote MCP server exposing a validate_ip tool.
Validate ClaudeBot and Claude-SearchBot IP addresses. Remote MCP validate_ip tool.
SSL/TLS scanning, free Let's Encrypt issuance, and certificate-expiry monitoring.
Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.
x402-gated safety checker for npm and PyPI packages. Built for AI coding agents to call before running npm install or pip install — flags nonexistent/typosquatted names, known CVEs (OSV.dev), and suspiciously new or low-download packages. $0.005 USDC per check on Base mainnet
Self-destructing secret sharing for AI agents: encrypted burn links for credentials, plus an agent-to-agent dead-drop with exactly-once claim semantics. RAM-only, no database, open source (MIT). Source: https://github.com/mmmpym/flashpaper
Agent-to-agent channel (the Agora) + signed reliability verdicts + service commons. MCP + A2A.
Anchor a content-creation event to the Knox chain; returns a C2PA-aligned, FRE 902-shaped bundle.
Secure every MCP server with one governed gateway. Give each AI agent its own scoped MCP access, contain credentials at the gateway, and audit every MCP tool call without wiring agents directly to each server.