Security analysis, scanning and identity.
AI agent identity verification for MCP and x402: check whether an AI agent is registered, Active and Verified in the Concordium Agent Registry (CIS-8004, ERC-8004 compatible). Library, Express middleware, MCP server and hosted pay-per-call API.
The official command-line interface for Creduent: the open standard and security protocol for cryptographic AI agent identity, authentication, and trust verification using Ed25519 and DNS.
Credential isolation for AI agents. Inject secrets at the network boundary.
Zero-dependency static security gate, integrity lock and provenance SBOM for AI Agent Skills and MCP configurations
AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI
Arcane Docker and Compose management over MCP and CLI with authenticated stdio and HTTP.
Pre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config.
WAFtester — the most comprehensive WAF testing CLI & MCP server
Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.
MCP server for conducting dynamic, conversational surveys with structured data collection.
Persistent autonomy infrastructure for AI agents
Mount an MCP server on an Elysia app: tools derived from the @elysiajs/openapi document, OAuth 2.1 resource-server enforcement built in
Read-only MCP server for markdown and agent steering files: read, outline, lint, context budget.
The one and only MCP Server for dads jokes.
Scan any URL for WCAG accessibility issues (axe-core) and get per-element fixes for an AI agent.
Access control for the AI agents your customers log in with (Claude in Chrome, ChatGPT agent, Codex, Comet): hide private data from them, ask the account owner's passkey before anything risky, sign every decision on your own server. Node.js middleware + b
Cybersecurity MCP server: 323 prompts + 7 workflows for red team, blue team, SOC, cloud, OSINT.
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
Remote proxy for Model Context Protocol, allowing local-only clients to connect to remote servers using oAuth
MCP security scanner and config linter for AI coding agents: finds exposed secrets, risky commands, broad permissions and invalid MCP servers in Claude Code, Cursor and VS Code (Copilot) configs. Local-first, no telemetry.