Enables an LLM agent to investigate a Kong Gateway through fourteen read-only, schema-validated tools and a deterministic diagnostic engine, so it can trace routes, services, plugins and upstream health and explain faults such as why authentication is failing on a path. Every fact comes from the gateway itself, and the model only selects tools and writes the evidence-backed explanation.
Provides AI-aware failover for Mihomo proxy on macOS by validating real OpenAI paths and switching proxy groups after verified hard failures. It offers a local stdio MCP server for diagnostics, status, and safe management of the AI proxy group.
Enables red-team and blue-team security workflows on BlackArch Linux by wrapping local tools like nmap, gobuster, nikto, and hydra as MCP tools, with scope-gating that prevents unauthorized scanning against any target not explicitly listed in a local scope.yaml file.
Enables discovery of public API operations, scoped read-only diagnostics for domains, DNS, and mail, and a controlled write lifecycle that requires independent human approval before any mutation.
Enables n8n AI agents to manage MikroTik routers via SSH/SSE, providing tools for firewall, DNS, DHCP, WireGuard, interfaces, queues, backup, users, logs, and routes.
Enables AI assistants to query system health, metrics, service reconnaissance, run multi-node patrols, and send incident alerts across distributed infrastructure through MCP tools.
MCP server that lets an AI agent manage Proxmox VE in natural language, with policy-driven security, read-only mode, two-step confirmations, and audit logging.
A simple MCP server providing ping, echo, and TCP host health-check tools with latency measurement. It enables transport testing and real network connectivity checks through natural language.
Enables AI assistants to manage pfSense firewalls using 17 tools for system status, firewall rules, DHCP, DNS, monitoring, and service management via the pfSense REST API.
Manage a fleet of OPNsense firewalls from an AI agent, inside guardrails it can't drive around.
MCP server for central management of OPNsense firewall fleets. 129 tools across devices, config sync, tasks, schedules, templates, backups and remote consoles - destructive actions confirmation-gated, MCP-issued tokens lifetime-bounded, backup and storage secrets excluded from the toolset entirely.
High-performance TypeScript MCP server for MikroTik RouterOS management, enabling Claude, GPT-4, or any MCP-compatible AI to manage routers through natural language with dynamic API discovery, VPN management, and configuration backup.
Enables users to check whether GPTBot, ClaudeBot, PerplexityBot, Googlebot and other AI/search crawlers can reach a specified page, distinguishing robots.txt blocks from server or firewall refusals.
Enables AI agents to invoke tools over a mutually authenticated TLS endpoint, with server-side certificate and identity checks plus fail-closed per-tool authorization through Open Policy Agent.
Enables network troubleshooting through an MCP Streamable HTTP endpoint, exposing diagnostic tools for Cisco Packet Tracer labs with human-in-the-loop review and NIST/CIS security validation.
Enables AI agents to safely troubleshoot networks through read-only tools for device inventory, interface status, VLAN paths, BGP neighbors, route lookups, and interface error detection. Integrates with Microsoft Copilot Studio and Teams for natural-language-driven network diagnostics.
Enables AI assistants to read endpoint/network inventory, security policies, the malware-hash blocklist, and scheduled/instant reports from Bitdefender GravityZone through its JSON-RPC API.
A production-ready MCP server that wraps Nmap to enable AI agents to perform automated network security assessments, including port scanning, host discovery, service detection, OS fingerprinting, and vulnerability scanning.
Enables AI assistants to read IT asset management, ITSM, and network inventory data from Alloy Navigator via its REST API, supporting object queries, activity logs, and reference-value lookups using OAuth2 application credentials.
Enables an AI assistant to run nine keyless, read-only verification lookups: Wayback page history, RDAP domain registration, DNS records, certificate transparency sub-domains, redirect-chain expansion, reverse-image search links, and locally computed sun position and shadow maths. Every result carries a caveat about what the lookup cannot show, and no tools exist for finding information about people.
Enables AI assistants to read device/sensor status, channel measurement history, and alarms from a Paessler PRTG monitoring instance via its REST API v2, with a read-only tool surface.
Enables AI assistants to read sites, hosts, device inventories, WAN/ISP health metrics, and SD-WAN configuration/status from Ubiquiti UniFi's Cloud Site Manager API.
Enables AI agents to perform passive reconnaissance, vulnerability intelligence, DNS analysis, and device search using Shodan's database of internet-connected devices, all from within your IDE.
Enables AI assistants to monitor Ubiquiti UISP network infrastructure through read-only REST API access to sites, devices, outages, logs, data links, gateways, background tasks, firmware, and speed tests.
Connects AI agents to an ASUS IPMI expansion card so they can see the host screen, control mouse and keyboard, read sensors, manage power, and update card firmware through MCP tools.
Provides AI assistants with read-only access to Cisco Umbrella's NextGen REST API for deployment, admin, policy, reporting, and investigate visibility, enabling DNS and cloud security monitoring through natural language.
Enables AI assistants to query internet-censorship rankings, incident evidence, shutdown-risk forecasts, and Sentinel calibration data, plus optionally use an agent relay for identity, messaging, tasks, and trust.
Enables AI clients to manage Huawei eNSP simulated network devices, execute CLI commands, apply configurations, and perform network diagnostics through natural language, with topology upload and visualization via a web UI.
MCP server that abstracts the Nginx Proxy Manager API, enabling management of proxy hosts, redirections, streams, certificates, access lists, and users through natural language.
Enables LLMs to create, onboard, and diagnose Cisco SD-WAN branch edges using MCP tools that interact with a FastAPI automation backend, with guardrails for safe operations.
Enables a chat session's owner to reach any host through arbitrary HTTP methods with custom headers and bodies, raw TCP sockets, outbound WebSockets, and browser-grade scraping that solves challenges and discloses explicit failover routing.
Voyager-net is a read-only, authorized network auditing MCP server that scans a single host or domain for DNS, port, TLS, and HTTP hygiene issues, returning findings with severity and suggested fixes. It enables AI agents to audit infrastructure safely without mutation, requiring explicit authorization.
Provides AI assistants with structured access to the Cisco Meraki Dashboard for managing organizations, networks, devices, clients, wireless, switching, and appliance operations.
Enables AI assistants to inspect and manage OpenStack clouds through 16 tools for servers, security groups, volumes, floating IPs, networks, backups, and safe preview-confirmed actions.
Enables authenticated remote MCP clients to manage a Kali Linux environment, run modular tools in sandboxed or optional host contexts, configure networking, and monitor jobs through a live WebUI.
Captures DNS queries leaving your Mac and serves them to Claude via MCP for traffic pattern analysis, answering questions about top domains, categories, and temporal patterns.
Enables AI assistants to investigate an RMM fleet (NinjaOne first) through read-only evidence collection and to propose exact, hash-bound plans for endpoint actions. Every write is refused until a human reviews the plan in a local dashboard and signs off with a WebAuthn passkey, after which dispatch is idempotent and verified by receipts.
Enables an AI agent to check whether a site is healthy and configured correctly by reading TLS certificates and classifying handshake failures, resolving DNS records from raw wire packets, tracing HTTP redirects and timings, and grading security headers with exact fixes. Every connection passes through an SSRF guard that vets and pins addresses so the agent cannot be aimed at internal networks.
Enables querying an F5 BIG-IP lab through read-only iControl REST calls, letting Claude inspect system and HA status, virtual servers, pool member health, monitors, and other objects via natural language. All tools are GET-only and paired with a read-only BIG-IP user role so nothing on the device can be changed.
Enables AI assistants to manage Cisco, Huawei, and H3C network switches over Telnet, SSH, or Console serial connections, with automatic vendor detection, paging and prompt handling, and cleaned command output. A local SSE web console streams every command and device response in real time so operators can watch what the AI is doing.
Enables full operational control over Contabo VPS/VDS infrastructure through natural language, including instances, DNS, snapshots, and more with 57 tools.
MCP server and CLI for Tailscale that lets agents inspect and manage tailnet devices, routes, users, keys, DNS, and ACL policy over stdio or streamable HTTP.
Read-only MCP server that surfaces UniFi network data from a UCG-Fiber console to Claude, enabling monitoring of hosts, sites, devices, clients, ISP metrics, and device stats via read-only API tools.
MCP server for managing TP-Link and Mercury Easy Smart switches via their web interface, enabling read-only status checks and VLAN/trunk configuration with dry-run support.
Enables AI assistants to bulk-check hundreds of brainstormed domain names in a single call, reporting which are available, taken, or reserved along with buy links and prices from multiple registrars. It runs locally via DNS, RDAP, and WHOIS lookups, with optional registrar API keys for confirming availability and premium pricing.