"A device or tool to control Home Assistant" matching MCP servers:

Enables control of Tuya smart lighting over the local home network, including reading device state, turning devices on or off by name, and switching between white and colour modes with RGB or temperature settings. Devices and credentials stay on the server and are scoped per household principal, so each caller only sees their own home's lights.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables natural language management of AdGuard Home DNS filtering, clients, DHCP, rewrites, and more via MCP.

Enables MCP-compatible AI clients to safely control Home Assistant devices and query MQTT sensors through natural language, using allowlist-guarded actions and pre-defined automations.

Enables MCP clients to securely inspect and control registered Windows PCs over a private Tailscale network, with risk-based approvals for actions such as launching apps, capturing screens, managing files, and simulating input.

An open-source MCP server that gives parents real-time oversight and guardrails over their children's AI agent interactions, with features like content filtering, spiral detection, and approval flows.

Enables management of Palo Alto firewalls through their REST API, including system information retrieval, PAN-OS upgrades, HA firewall management via Panorama, content updates, and certificate management.

Enables centralized proxy and orchestration of MCP servers, providing unified tool discovery, authentication, and secure request routing. It adds a human-in-the-loop approval gate for high-risk actions and audit logging.

A governance and control layer for MCP tools that manages tool requests as intents through policy-based approval, queuing, or blocking. It enables secure human oversight and audit trails for consequential agent actions across platforms like Claude Desktop and Cursor.

Enables AI agents to issue allowlisted commands to a Ring-verified owner’s enrolled home devices, with execution confirmed only after the owner’s Mac returns a signed receipt.

Enables an AI assistant to diagnose a broken application on a local Kubernetes cluster by inspecting pods, events, and logs, with server-side guardrails, least-privilege RBAC, and an audit log. It can also restart deployments in allowed namespaces only after a dry-run preview and host approval.

A secure tool-execution plane for agentic AI that enforces JWT authentication, rate limiting, prompt-injection inspection, and audit logging, while ingesting downstream OpenAPI endpoints as MCP tools.

Enables managing FortiGate firewalls from an MCP-compatible AI client, with local multi-device enrollment, OS credential storage, connectivity checks, and AI client integration.

Protects AI agents from bad tool outputs, schema mismatches, and tool poisoning by validating, sanitizing, and scoring reliability of tool responses.

Enables OAuth-authenticated MCP clients to list registered SwitchBot devices, read their status, and switch plugs on or off via a Cloudflare Workers deployment. Access is limited to an allowlisted set of devices, and turning off a PC plug requires the caller to confirm a clean shutdown first.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

The control plane for AI prompts that scores, enforces policy, locks config, and audits every prompt decision.

MCP server providing 100% coverage of the CISO Assistant GRC REST API through action-routed tools for compliance, risk management, and other security domains.

Secures MCP tools as an OAuth 2.1 resource server, validating short-lived delegated tokens, enforcing policy-as-code, and auditing AI agent actions.

Enables agents to check third-party tool licenses, validate vendor policies, and issue license receipts before using external tools.

Enables declaring a catalog of tools for LLMs, filtering them by role, validating arguments, guarding sensitive calls with server-side confirmations, and recording an audit log.

An enterprise MCP server scaffold that provides secure, governed access to internal tools through RBAC, audit logging, rate limiting, and prompt-injection boundaries, with a FastAPI control plane and OpenTelemetry observability.

Enables verification of deployment-scoped model-visible DSH tool surface conformance by checking recorded tool identities and schemas against approved locks, reporting only drift categories and hashes.

An MCP server that automates CI/CD pipeline creation, analysis, and security enforcement. It generates production-ready pipelines from templates and enforces DevSecOps best practices.

MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.

Enables agents to search across the pooled tools of many connected MCP servers and invoke them through a single endpoint, returning only the handful of tools relevant to each request. Filters by the caller's permissions before ranking, so agents never see or plan around tools their user is not allowed to use.

Enables MCP clients to fetch the signed-in Microsoft Entra user's profile from Microsoft Graph via the GET /me endpoint using the provided bearer token.

Enables AI agents to securely discover, invoke, and manage tools through a hardened MCP endpoint with protections like injection detection, circuit breakers, retry backoff, response caching, context-window limiting, and state snapshots.