Security MCP Servers

CSOAI DEFONEOS — UK defence-AI measurement surface (DEFONEOS-SEAL living attestation + MITRE ATLAS + governance crosswalk + audit chain). Measurement, not certification.

MCP server for agentbond — AI agent authorization and governance

Hash passwords with bcrypt and issue/verify JWT session tokens.

APOA authorization for MCP servers — per-tool-call scoping, delegation chains, audit trails

Google Ads API integration for Model Context Protocol (MCP) with refresh token authentication

SecureMCP is a security auditing tool designed to detect vulnerabilities and misconfigurations in applications using the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction). It proactively identifies threats like OAuth token leakage, prompt injection vulnerabilities, rogue MCP servers, and tool poisoning attacks.

Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.

An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for authorized cybersecurity research workflows.

Demo agents showcasing CapiscIO Agent Guard and MCP Guard — trust badges, identity verification, and tool-level authorization for A2A and MCP protocols

- Collection of Google-native tools (Gmail, Calendar, Drive, Tasks) for MCP with OAuth management, automated token refresh, and auto re-authentication capabilities.

Gmail Postmaster Tools v2 — domains, traffic metrics, and compliance via your own Google OAuth.

Give AI agents a real email address, vault, calendar, and task delegation via MCP.

Samsara fleet management — vehicles, routes, drivers, HOS compliance. Unofficial, bring your token.

MCP server for credential isolation — bots use passwords and API keys without seeing them

Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.

Automated website compliance infrastructure and GDPR/CCPA auditing.

Read-only runtime secret retrieval from HashiCorp Vault via Keymaster for autonomous AI agents.

MCP server that inspects TLS certificates, cipher suites, and protocol configurations for any domain

MCP security proxy — Trust Score checks, DLP scanning, and policy enforcement for every tool call

MCP server for Concept2 Logbook API with automatic OAuth2 authentication

Model Context Protocol audit tool for analyzing project dependencies and generating audit reports

MCP server that audits websites for **RGAA 4.1.2** accessibility compliance. Connects to Claude Desktop and exposes two tools: automated page auditing and RGAA criteria lookup.

MCP server for AgentGate — AI agent payment authorization and governance

Secure Model Context Protocol (SMCP) v1 - Production-ready security framework for MCP implementations