"Security" matching MCP servers:

Provides a security governance layer for AI agents to safely access upstream MCP servers, enforcing tool-level RBAC, parameter constraints, authentication via static tokens or OIDC, and tamper-evident audit logging.

Standalone MCP server exposing only the security-classified tools from Shade Browser, enabling Brave CDP browser automation across 20 isolated profile slots. Built on FastMCP and Playwright Python.

Connects AI agents with the CrowdStrike Falcon platform to enable intelligent security analysis, providing programmatic access to detections, incidents, threat intelligence, vulnerabilities, and other security capabilities for advanced security operations and automation.

Enables access to agent instruction files and prompts for AI development workflows. Provides tools to retrieve and list development rules, security checks, and common prompts from an agents library through MCP protocol.

A system-level MCP protocol stack for OpenHarmony that provides unified tool discovery, caching, security, and statistics for agents, reducing context overhead and improving throughput via a user-space daemon (mcpd).

A security MCP proxy that monitors and blocks data exfiltration between AI agents and their tools by detecting toxic flows (untrusted → sensitive → egress) deterministically with zero LLM calls in the decision path.

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

An MCP server for domain-agnostic task orchestration, turning objectives into executed workflows with built-in validation, security, and multi-agent patterns.

Enables Microsoft Copilot Studio agents to fetch and deliver jokes on demand through the Model Context Protocol. It is published as a Power Platform custom connector, so access benefits from enterprise security, governance, and real-time data capabilities.

An MCP server that connects AI agents to the CrowdStrike Falcon platform for intelligent security analysis and automation across various security modules. It provides programmatic access to detections, incidents, host management, and threat intelligence to enhance security operations within agentic workflows.

An MCP task broker that enables Claude and Codex/ChatGPT agents to delegate tasks to each other, with persistent queues, worker adapters, and security controls.

An MCP control plane for Codex native sessions, translating eight explicit operations with strict security boundaries for authenticated access through OpenAI Secure MCP Tunnel.

Enables secure Docker command execution from isolated environments like containers through MCP protocol. Provides tools for managing Docker containers, images, and Docker Compose services with security validation and async operation support.

A URL security scanner and MCP server that enables AI agents to analyze URLs for phishing, malware, and other threats before navigation, with optional intent alignment checks.

A Model Context Protocol server that transforms video downloading into a tool-based system for LLM orchestration, allowing users to download videos from 1000+ platforms with intelligent workflows and security features.

Facilitates interaction and context sharing between AI models using the standardized Model Context Protocol (MCP) with features like interoperability, scalability, security, and flexibility across diverse AI systems.

Enables AI agents to safely call MCP tools through a security gateway that enforces per-role authorization and least-privilege tool scoping.

A local-first security gateway and visual dashboard for AI agents that enforces cost caps, blocks prompt injections, and requires approval for dangerous actions.

A security-focused MCP server that enables automated log retrieval and threat analysis using LangGraph orchestration and RAG. It allows users to detect suspicious activity and generate structured security insights by integrating LLM reasoning with log data and runbook documentation.

Enables remote browser automation via MCP, allowing models to open pages, read snapshots, click, fill, and select elements using Playwright, with built-in security restrictions against sensitive actions.

Transforms stdio-based task tools into a stateful Streamable HTTP MCP server, enabling multiple clients to manage tasks via URL with session isolation and security checks.

Enables orchestrating multi-agent AI coding workflows with Git worktree isolation, parallel testing, and security scanning via the Model Context Protocol.

A local MCP server that lets Claude Code orchestrate Codex CLI and OpenCode CLI as sub-agents with strict security, concurrency, and output limits.

A local-first middleware proxy that proxies multiple MCP servers through a single entry with schema minification, semantic routing, security hardening, and state guard.

Local-first MCP proxy with BM25 tool discovery, quarantine security, Docker isolation, OAuth support, activity logging, and web UI. Routes multiple upstream MCP servers through a single endpoint.

Enables AI assistants to interact with Fastly's CDN API through the Model Context Protocol, allowing secure management of CDN services, caching, security settings, and performance monitoring without exposing API keys.

A local MCP bridge that lets a compatible host start, monitor, steer, interrupt, resume, and approve Codex app-server work while enforcing repository-root security.

Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging across LangChain, OpenAI, Anthropic, and MCP.

Provides access to over 100 curated AI agent skills from organizations like Anthropic, Vercel, and Hugging Face. It enables AI assistants to perform specialized tasks including document processing, security analysis, and web development through a standardized interface.

An MCP server that lets OpenAI Codex delegate tasks to Google Gemini agents as isolated background workers, with Git worktree isolation, loop detection, and security boundary enforcement.