MCP servers for security scanning, vulnerability testing, secrets management and QA automation. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.
MCP server for Firegex — CTF regex/proxy firewall
Official Anchore Grype MCP Server for AI-assisted vulnerability scanning
A lightweight guardian/middleware for MCP servers (auth, rate-limiting, logging, WAF, etc.)
MCP server for Hejdar — runtime policy enforcement for AI agents
Lightweight, plug-and-play AI safety middleware that protects humans.
MCP server for extracting metadata from Korean HWP/HWPX files
Live threat intelligence MCP server — IP lookup, CVE intel, KEV Oracle predictions, malware hashes, pre-attack staging detection. Free, no API key required.
MCP server for controlling LeCroy oscilloscopes via SCPI/VXI-11
MCP server exposing llm-behave behavioral regression testing as Claude tools
Allure TestOps MCP Server
MCP server for Lumu Defender API integration with Claude Desktop
MCP server for MailPal -- free email for AI agents with hardware attestation
MCP security scanner plugin - scan your installed MCP servers with 16 engines
MEOK MCP Hardening MCP — automated security red-team for any MCP server. Maps OWASP LLM Top 10 (2025) + 5 MCP-specific risks to a 0-100 hardening score with HMAC-signed reports. By MEOK AI Labs.
MEOK MCP Test MCP — golden-file + schema-drift + tool-failure tests for any MCP server. Drop-in pre-publish gate. Generates pytest templates. HMAC-signed test reports + Shields.io grade badge. By MEOK AI Labs.
MCP server to generate and run mock APIs from specifications.
MCP server for agent-safe Obsidian vault access with lint validation
Security-first, version-agnostic MCP gateway for Odoo 17/18/19 — works with stock and custom modules via YAML configuration
The Okta Open Source MCP Server integrates with LLMs and AI agents, allowing you to perform various Okta management operations using natural language and is Generally Available (GA).
Python SDK for the oktsec security proxy — identity, policy, and content scanning for AI agent communication
MCP server for verifying AI agent claims vs reality — inline grounding-check on retrieval context, swallowed-exception scanner on agent-written code, and multi-turn transcript review for unverified completions + cross-turn contradictions. Sub-second, local, free, MCP-native — the lightweight complement to dashboard-based eval frameworks (DeepEval, Phoenix, LangSmith).
Drop-in MCP proxy that keeps your secrets out of the context window
Palo Alto Networks AI Security MCP Relay
Panther Labs MCP Server