"A server for identifying bugs in the terminal related to cursor issues" matching MCP servers:

Enables AI agents to open persistent interactive terminal sessions with network devices over SSH, Telnet, TCP console, or serial, write raw commands including nested ssh/telnet transitions, and read full output without requiring a particular prompt format. It supports multiple concurrent sessions and keeps credentials/secrets out of MCP arguments or audit logs.

Enables natural language management of MikroTik routers through Cursor IDE by translating requests into RouterOS commands via API or SSH.

Local MCP server (stdio) exposing the entire Hetzner Cloud API as 201 typed tools, read and write

the-real-unifi-mcp License: MIT Node MCP SDK [![CI](https://github.com/mguttmann/the-real-unifi-mcp/actions

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.

An unofficial MCP server that connects AI assistants to Akamai APIs, providing tools for edge diagnostics, debugging, and network analysis.

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.

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.

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.

A PROXMOX implementation containing 152 tools covering QEMU VMs, LXC, unified guest power, storage admin, cluster/tasks, snapshots, backups (incl. scheduled jobs), migration, HA, firewall (incl. IPSet CIDRs), access control, replication, SDN (read), ACME (read), pools, and console tickets.

Enables AI agents to access curated SIP/VoIP documentation, troubleshoot traces, and analyze telecom configurations with 20+ read-only tools.

Enables interaction with The Things Industries LoRaWAN platform via MCP tools, supporting application, device, gateway, and webhook management.

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

This MCP server helps debug legacy devices behind proxies in OT environments by analyzing web interfaces and generating custom rewrite rules to fix proxy-related issues.

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.

Operate packet-radio digipeater nodes from Claude and other MCP clients.

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 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.

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.

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.

Self-hostable MCP server for WhisperGraph — a graph of 7.39B nodes / 39B edges mapping DNS, BGP, GeoIP, WHOIS, and threat intelligence. Six read-only tools (Cypher query + schema introspection + threat assessment), six resources, eight investigation prompts. stdio and Streamable HTTP transports.

Model Context Protocol server for the NetLoc8 IP geolocation API. Gives AI assistants access to country/city lookup, timezone reconciliation, and IP utilities.

An MCP server that lets an AI assistant manage your Keenetic router in plain language — list connected devices, pin static DHCP leases, rename devices, check WAN status, and reboot.

A read-only MCP server that enables Claude to audit Firewalla network security configurations and monitor network activity. It provides tools to inspect devices, rules, alarms, and traffic flows without making any changes to the Firewalla system.

Infrastructure access broker for AI agents — SSH & Kubernetes. Per-operation ephemeral credentials minted by a separate signer; the model never touches one. MCP stdio / HTTP+OIDC.

Enables AI to query live weather, domains, IPs, DNS, SSL, currency rates, and more via the APIFreaks API.

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.

Lets an agent mint and manage its own hostnames on DNSMint, through the Model Context Protocol.

Enables agents to run SEO and AI-search readiness audits (llms.txt, crawler access, sitemaps, structured data, redirects, indexability, and more), look up startup revenue listings and leaderboards, and check a domain's SPF, DKIM, DMARC, and MX records with concrete fixes. Runs locally over stdio with no account or API key, and frames all third-party responses as untrusted data.