Security & Testing MCP Servers for Codex CLI

Agent Incident Relay MCP — Article 73 5-clock broadcaster. One incident → simultaneous signed

Credential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.

Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats

Flags the EN 301 549 clause each line breaks, and separates what is in force today from what arrives

MCP server for home network discovery and vulnerability scanning

MCP server for Konduto — Brazilian fraud prevention: order risk scoring, device intel, lists

DEPRECATED: no live endpoint (collection-prod.inspcdn.net does not resolve)

Local verification of nomue Protocol Records; current release supports the Release 1 Welch bundle.

Verifies Ed25519-signed attestation records and builds audit reports via MCP tools.

Payment firewall for x402: scans for replay, overpayment, PII/secret leaks, prompt-injection.

Signed time and SHA-256 witness receipts for agents, with offline verification and x402 payment.

Run bounded, deterministic MCP reliability tests and generate executable regressions.

Scan suspicious messages, URLs, and text for scams with AI. Free tier - no API key required.

MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.

A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.

Finds the 12 author-side privacy duties your plugin PHP breaks, with the article and the fix on ever

Classify AI systems under the EU AI Act and generate Article 50 transparency notices.

npm, PyPI & crates.io health, vulns and dependency graphs. Runs locally, no API key.

Agent Content Watermark MCP — dedicated EU AI Act Article 50(2) GenAI watermarking. Visible +

Validate tool-call args before execution. Returns LLM-friendly retry hints.

BugBrain QA platform for AI coding tools: autonomous exploratory testing, test plans, a11y audits.