Security & Testing MCP Servers for ChatGPT

Live threat intel for Claude — CVE, KEV predictions, IP lookup, malware hashes. Free, no API key.

Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.

Official LiteSOC MCP (Model Context Protocol) Server — gives AI editors direct access to your security alerts, events, and forensic

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

MCP server adapter for MCP Workbench — expose inspect, generate, and test capabilities to AI agents

DPIA generator for the EDPB harmonised template (adopted 14 Apr 2026) with EU AI Act Article 26(9)

EU Cyber Resilience Act (CRA, Regulation (EU) 2024/2847) compliance MCP server. 4 tools, 11 tests. A

MCP server exposing PatrowlIntel vulnerability intelligence (CVEs, EPSS, CISA KEV, public exploits, trending attacks).

Classify any AI system under the EU AI Act: risk tier + binding Articles, verbatim from the law.

Gating proxy for MCP servers: policy, verification and one audit trail across upstreams.

Synthetic time-series test data with trend, seasonality, noise, and anomalies, for any MCP client.

Local supply-chain CVE scanner via OSV/NVD. Scans deps and IDE extensions. No upload.

Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.

Trust Chain MCP server. Tools: create trust anchor, verify chain, add attestation. Built by MEOK AI

Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.

MCP server to mount and unmount VeraCrypt containers with secure stdin password handling.

Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs

MCP server for ALTR data security: databases, tags, policies, classification, access, audits

Contextual blast-radius scoring for shell commands an AI agent is about to run

MCP server for MITRE Caldera adversary emulation platform

Certificate Transparency search for AI agents: certs, subdomains, issuance history, expiry.