MCP server for the @agentutility prooflayer cluster — pay-per-call x402 tools, no API keys, USDC on Base.

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic code review, auto-fix. For Claude Code, Cursor, Windsu

JavaScript/TypeScript SDK for ProofLayer — the blockchain for digital truth

AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.

Lightweight, zero-Python security scanner MCP server for AI coding agents. Fast install (~5s), 1700+ vulnerability rules with pure JavaScript regex engine, 4.3M+ package hallucination detection. For Claude Code, Cursor, Windsurf, Cline.

Lightweight MCP security scanner for AI coding agents. 400+ YAML rules, tool-poisoning detection, prompt injection scanning, package hallucination checks, auto-fix generation, and optional LLM deep audit. MIT licensed, fully offline-capable.

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix. For Claude Code, Cursor, Windsurf, Cline, OpenClaw.

Standalone offline verifier for Proof Layer receipt bundles. Ed25519 signature verification, SHA-256 hash chain validation, and Merkle root computation. Zero external dependencies.

Cryptographic governance receipts for AI agent actions, exposed via Model Context Protocol. Ed25519-signed, hash-chained, independently verifiable offline. Drop-in for Claude Desktop, Cursor, Cline, and any MCP-aware host.

Official Proof Layer Node.js SDK — submit AI agent action proposals for governance, retrieve Ed25519-signed receipts, and verify hash-chained audit trails. Drop-in for any Node service that needs cryptographic proof of agent decisions.