Security MCP servers

Discover mobile app attack surfaces via BeVigil OSINT — hosts, subdomains, URLs, and more.

Gate/Prove: deny unattended destructive agent tools. Instant Audit $499 on a2zsoc.com.

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

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

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

Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.

Verify email addresses, clean lists, and audit a domain SPF, DKIM, DMARC and MX setup.

Reverse-engineering evidence from a running Windows process, not the binary on disk.

Transparent MCP proxy that independently re-verifies tool-call claims before the Host trusts them.

Policy proxy for MCP tool calls. A denied call never reaches the downstream server.

Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)

Check any MCP server or agent skill before installing: upkeep, real adoption, and OSV advisories.

Live honeypot threat intel: attacker IPs, IOCs, credentials, payloads, actors.

Privacy-first Danish caller ID, CVR company lookup, operator data, and community spam signals.

End-to-end-encrypted, sovereign inbox for AI agents. The server only ever sees ciphertext.

Screen the counterparty of an x402 payment before an agent pays it. Runs offline by default.

MSP MCP for CIPP: Microsoft 365, Entra ID, Intune, Exchange, Defender and GDAP across all tenants

Local verification of nomue Protocol Records; current release supports the Release 1 Welch bundle.

MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.

Local credential broker: agents call APIs, SSH and DBs via scoped presets; secrets stay in keychain.

Anonymize client files on your computer before Claude reads them; real values restored locally.

Deadline-aware governance for AI agents: PII scan always, safety check if it fits the deadline

Safety-first OPNsense firewall MCP: read-only by default, planned and auto-reverting writes.

Use passwords and API keys from your KeyZula vault without the assistant seeing them.

Run commands, transfer files and browse assets on a JumpServer v4 bastion from your AI assistant.

MCP server for Box admin-log analytics — external-sharing visibility, read-only

AI-powered Kubernetes diagnostics, RBAC analysis, security checks, and app deployment via MCP

Policy-enforcing MCP proxy with portable evidence output.