Michael King

MCP server: 10 deterministic web utility tools for AI agents — read URLs as Markdown, unfurl metadata, validate email, scrape with CSS, parse feeds, DNS/RDAP/SSL/HTTP/structured-data.

MCP server: input/output safety gate for AI agents — detect prompt injection/jailbreak, vet URLs & IPs, check pwned passwords (HIBP k-anonymity), scan for leaked secrets & PII. Deterministic, free, no LLM.

MCP server: pre-send risk check for AI agents that move money — screen a crypto address (or ENS name) and payment URLs for OFAC sanctions, scam/abuse blocklists, and on-chain risk before a transfer. Deterministic, no LLM.

MCP server: the pre-install supply-chain guard for AI coding agents — verify a package exists (catch slopsquat/hallucinations), check vulnerabilities & malware (OSV), detect typosquats, audit a whole dependency list. Deterministic, free, no LLM.

MCP server: email safety for AI agents — scan inbound email for 'AI agent phishing' (prompt-injection/spoof) before acting, and outbound email for secret/PII leaks + deliverability before sending. Deterministic, free, no LLM.

MCP server: security scanner for AI-generated code — the agent scans its own code/diff before committing. Detects injection, SSRF, hardcoded secrets, weak crypto, unsafe deserialization, TLS-off, XSS. Deterministic, free, no LLM.

All six agent guard suites in one local MCP server, with optional cloud intelligence.