Security MCP servers

Decode PEM certificates, check expiry and inspect a live TLS certificate, all offline

Read-only MCP server checks and quote verification, free and keyless; results signed and publicly lo

Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.

Deterministic security layer your AI can't be. 624 rules, 39 tools, CLI + doctor + host audit.

Audit your own smart-home devices: destinations, encryption, open ports, A-F grade.

MCP server for the Frame security scanner: scan, verify, fix, exploit, packs and separation logic.

Supply-chain malware scanner and MCP server: vet packages in 15 ecosystems before install, offline.

Adopt, read, verify and record an Open Entity identity (OEIS-1). No auth, no CAPTCHA.

Manage MagicSword endpoints, alerts, policies, and private intelligence through MCP.

Manage Keycloak users, groups, roles and realms through the Keycloak Admin REST API.

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

Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.

SSH for AI agents: commands, files, backups and health, with approval, a vault and an audit trail

Keycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.

Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.

Zero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance.

Passport, mandate, fail-closed action gate and tamper-evident journal for AI agents.

Offline receipt verifier. Ed25519 signature verification without contacting any server.

AynOps is a reconnaissance focused MCP Server which gives reconnaissance capabilities to AI Clients

Human approval gate for AI agents: risk-scored requests that only a person can approve

Pre-sign EVM tx/approval safety for AI agents: decode calldata, flag drainers, return GO/HOLD/BLOCK.

Local vulnerability scan on top of grype, with prioritised upgrade actions for agents.

MCP server for creating and managing SOPS-encrypted secrets

Checks ML model files (pickle, PyTorch, joblib, NumPy, GGUF, ONNX) for code that runs on load.

Website safety and trust analysis. Verify domain reputation and detect phishing with GridinSoft.

Permission-gated superuser (sysadmin) MCP agent with enterprise guardrails and audit.

Tells your AI agent which vulnerabilities to fix first, using OSV.dev, FIRST EPSS, and CISA KEV.

MCP server for the Frida reverse engineering toolkit.