Security MCP Servers

A local security firewall, scanner, and audit layer for Model Context Protocol servers.

AI-powered URL safety validator MCP server. SAFE/SUSPICIOUS/DANGEROUS verdict for agents.

Enforcing proxy for MCP tool calls: every tools/call is checked against an FDIA policy before it reaches the server, with a hash-chained audit log.

Static pre-install security scanner for MCP (Model Context Protocol) servers — `npx mcpaudit <path>` flags command injection, credential/env exfiltration into LLM-visible output, over-broad filesystem/tool scope and dynamic eval before you wire a server i

Model Context Protocol (MCP) server for interacting with Nuclei vulnerability scanner

Role-based authentication and tool filtering plugin for LokiCMS MCP servers

Free, in-process scanner for MCP (Model Context Protocol) servers — detects tool poisoning, typosquats, hidden unicode, base64 payloads, and exposed transports. Same regex / scoring engine that ships with the VyriAI control plane.

MCP server for querying CrowdStrike LogScale logs

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

Encrypted secrets for Next.js. AES-256-GCM with no vault needed.

A complete MCP server template that include vitamins (oauth authentication included)

Local memory infrastructure for AI agents. Store knowledge and skills in isolated vaults you compose, control and query.

MCP gateway for AI agents — prompt-injection defense, token savings, deterministic policy, OAuth, per-agent profiles

VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection.

Local-first knowledge vaults for project docs and specs. Tagged, versioned, full-text searchable.

Code review as an MCP server — structured reviews with OWASP security scanning.

Scan MCP servers and agent tool manifests for poisoning, exfiltration, secrets and supply-chain risk

Self-hosted firewall for AI agents — a transparent MCP gateway that intercepts every tool call, applies an allow/deny/ask policy with human-in-the-loop approval, and streams an audit trail to your own control plane.

MCP server for ClassiFinder — secret scanning tools for AI agents

MCP server security scanner with runtime behavioral verification — checks that tools actually do what their descriptions claim.

A Model Context Protocol server for challenge management with authentication

Customer-installable MCP server for the Hebbian tenant brain (Python). Same 13 tools as the Node.js sibling @hebbianvault/mcp.

Code similarity firewall - blocks dangerous code patterns before they reach execution tools