"Understanding How to Use a Browser" matching MCP servers:

Enables LLMs to configure Tencent Cloud resources such as DNSPod DNS records and CVM/Lighthouse security group rules by controlling a locally logged-in Edge browser over CDP, leveraging existing login state without needing API keys or credentials.

Exposes any stdio-based MCP server over the MCP Streamable HTTP transport so remote clients can reach it, spawning an isolated child process per session and gating access behind a secret URL path.

Enables AI agents to manage VPN infrastructure through provisioning, lifecycle control, traffic routing, and health monitoring.

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.

Enables LLM agents to read 3x-ui panel data and perform full CRUD operations on inbounds and clients.

Enables MCP agents to run RouterOS commands on MikroTik routers over SSH, with configurable profiles, secure authentication, and a read-only safety guard.

A domain security and privacy checker MCP server that runs locally, performing DNS, TLS, HTTP, and RDAP lookups to generate a scored report covering certificates, email authentication, DNS, and web security headers.

Read-only access to a local Hiberden backup catalog: list projects, archives, tapes, and jobs, check 3-2-1 coverage, and verify a stored copy by reading it back and re-hashing it. Runs against the catalog on your own machine, so nothing leaves it.

See which process holds a local port and who started it, find free ports, wait for services, and stop a dev server safely. Fixes "port already in use" (EADDRINUSE) for AI coding assistants. Never stops system processes; Docker and WSL ports get the right stop command. Run with: npx -y portcheck-cli mcp

Diagnoses a domain's email authentication — SPF, DMARC, DKIM, MX, blacklists and domain or SSL expiry - and returns copy-paste fix records generated by a validating engine, never a language model. The MCP server is hosted remotely; this repository carries the plugin manifest, connector config and bundled skill.

An MCP server that lets Claude monitor and manage a TrueNAS box in plain English. It is deliberately read-only, providing tools to check alerts, storage pools, snapshots, services, and more.

Enables AI clients to run read-only network diagnostics over a sample multi-site topology, including site health, degraded sites, root-cause analysis, and redundancy gap detection.

Enables MCP clients to search, describe, and call roughly 180 undocumented UniFi OS/Network console API operations from a bundled OpenAPI spec, plus curated reads and typed configuration changes. Writes are off by default, require per-entity enablement, and use previews, verification, and rollback safeguards.

Provides DNS lookup and email authentication diagnostic tools (SPF, DKIM, DMARC, MX, etc.) for use with MCP-compatible clients. Enables natural language queries to check DNS records and email health.

Exposes FFraud's fraud-detection tools so assistants can score a website's security, rate any IP for fraud and VPN/proxy/Tor use, and flag disposable emails, throwaway-mailbox domains, and community IP reports. It runs as a remote MCP endpoint or locally over stdio with no API key required.

Enables AI agents to run privacy-first network diagnostics (egress IP, proxies, DNS, port checks, security-header audits), handle authentication primitives like TOTP and disposable inboxes, and use developer utilities such as URL-to-markdown reading, webhook inspection, hashing, file/paste sharing, and read-only EVM RPC calls. All tools are free, require no API keys, and operate under a zero-log policy with automatic expiry.

Converts plain-language storage requests into validated Hitachi raidcom command lines and multi-step shell scripts, including ready-made provisioning recipes, command lookup, and model limit checks. It is build-only: it never connects to a storage system, runs a command, or holds credentials, returning reviewed command text for a person to execute.

A Model Context Protocol (MCP) server for the RIPE Atlas network measurement platform. Enables AI assistants to create network measurements, retrieve results, search probes, and manage credits.

A Model Context Protocol server that enables AI assistants to read and safely modify TP-Link Omada networks through capability-gated tools, with a default read-only profile and dry-run writes for security.

MCP server for the Zabbix API that provides a daily_brief summary of active problems and category-specific metrics, along with tools to query problems, hosts, and item values.

Use the MCP servers on your computer from a cloud AI agent: one authenticated Streamable HTTP endpoint, an outbound WebSocket from your computer (no inbound port), and stdio and HTTP servers aggregated under aliases with per-server tool allowlists.

Look up any IP address with FindIP: geolocation, network and ASN, and VPN, proxy, Tor and datacenter detection. For websites that use FindIP Shield, list the recent risky visitor events and explain the reasons behind one event.

Control your UniFi network via AI with a lightweight 2-tool MCP server that supports both cloud and local UniFi controllers.

Connect your agent to a live, P2P mesh of other agents and consumable mesh services.

Enables an agent to administer a Linux host (with first-class Arch support) over SSH through 109 typed tools covering system state, systemd, journal, packages, network, disks, hardware, boot, sessions, users and security, all returning compact JSON. Reads are the default, while mutations require write mode plus a single-use confirmation token, with optional sudo for root-level operations.

A Model Context Protocol server that wraps the Namecheap API, enabling AI assistants to manage domains, DNS records, SSL certificates, and account information.

A local Model Context Protocol (MCP) server that allows an MCP client such as Codex to discover and call Cisco Nexus Dashboard APIs for inventory, health checks, troubleshooting, and controlled configuration changes.

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.

Thin MCP server for Cisco CML2 that exposes the live OpenAPI specification and a generic API call tool, enabling models to interact with CML2 by reading the spec first.

Provides a secure, job-oriented MCP connector for NetBox device lookup, enabling retrieval of device identity, status, site, role, and primary IP by name or ID without write access or bulk enumeration.

Enables AI agents to manage Tophost DNS records through MCP tools, including listing, creating, updating, and deleting records with safety guards, while delegating authentication and Tophost protocol handling to a separate REST API service.

Enables any MCP client to look up CVE intelligence — severity summaries, filtered searches, and full per-CVE detail fusing NVD, MITRE-CNA pre-NVD, CISA KEV, EPSS, and GitHub GHSA data — alongside a Shodan-derived internet-exposure footprint showing how many internet-facing services run a version mapping to a given CVE. It is free, keyless, and read-only, and distinguishes verified zeros from unassessed or failed lookups.

Provides tools to classify, test, and expand IPv4/IPv6 addresses using Node's built-in net module.

Connects an AI assistant to a PowerEdge server's iDRAC 8 over Redfish so it can report hardware health, sensors, inventory, firmware versions, logs and BIOS settings, all read-only by default. With additional permission modes it can also power the server on or off, restart it, control the identify LED and boot device, and change BIOS configuration.

A universal digital fingerprinting MCP server that combines 103 techniques across TCP, TLS, SSH, HTTP, DNS, and more into a single interface for AI agents, enabling full-spectrum fingerprinting on demand.

Enables agents to search and call the full OPNsense core and plugin API, perform model-validated CRUD and settings operations, and use curated firewall, service, and network tools with optional auto-revert writes.

Enables Claude to read and manage a DNS server on the user's own machine through its HTTP API, covering stats, settings, zones, logs, users, ad blocking, cache flushing, and DNS records. Every call carries a safety level, so read actions run immediately while changes and destructive operations require explicit confirmation, with credentials kept local and downloads written to disk rather than chat.

A read-only MCP server for OpenWrt routers with Nikki and Mihomo that provides diagnostics like network snapshots, flow inspection, and packet capture to help agents troubleshoot network issues.

Enables agents to securely manage Cloudflare DNS records for iveseenu.com only, including listing, querying, creating, updating, upserting, and deleting A, AAAA, CNAME, and TXT records with dry-run and safety restrictions.

Provides MCP servers for VPN control (NordVPN) and torrent lifecycle management via Jackett search and qBittorrent operations, plus a unified CLI.