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 assistants to manage a Telgea business mobile operator account end to end: users, teams, plans, lines and eSIMs, live connection status, number port-ins, usage and analytics, data pools, rates and cost thresholds. Read-only tools run by default, while costly or irreversible changes such as new lines, SIM swaps, port-ins and terminations require a signed two-step prepare/commit flow, with eSIM credentials redacted everywhere except a separately gated tool and daily API request budgets enforced locally.
infomaniak-mcp-agent lets Claude (or any MCP client) drive a real Infomaniak account end-to-end through 54 tools — web hosting, mail, kDrive, domains, DNS, DNSSEC, FTP/SSH users, AI catalogue and more. Every destructive operation goes through a strict two-phase commit (plan + single-use confirmation token) so the agent can never silently mutate your account. Open Source
Enables AI agents to search for, purchase, connect, and verify custom domains end to end, including setting up email records, configuring forwarding, diagnosing drift, and confirming TLS issuance without handling DNS records directly. It offers twelve hosted tools covering domain availability, registration orders, provider discovery, and account-wide connection inventory.
Enables intelligent troubleshooting, monitoring, and configuration of Cisco Meraki networks through natural language, with agentic workflows for automated diagnostics and health checks.
Enables AI agents to drive wireless penetration testing end-to-end through MCP, including monitor mode, network scanning, handshake and PMKID capture, WPS attacks, deauthentication, and password cracking. It exposes all h4kfi tools to MCP-compatible clients like OpenCode and Claude Code.
Enables Claude to operate a Hetzner estate end to end — Cloud servers, Cloudflare and Hetzner DNS, SSH hosts, and Coolify deployments, plus multi-step recipes — through 53 tools. Writes are dry-run until confirmed, protected servers refuse destructive calls, and every call is audited with secrets masked.
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.
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 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.
Enables MCP agents to run RouterOS commands on MikroTik routers over SSH, with configurable profiles, secure authentication, and a read-only safety guard.
Enables AI assistants to view devices on a Portveil account and move, rotate, reconnect, or disconnect them across VPN locations, with verified successful moves.
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.
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.
Answers "what is this IP" by matching addresses against a synced local copy of Azure service tags and live reverse DNS lookups, including the reverse direction of listing every CIDR prefix for a given service-tag name. Every answer is honestly labeled with the source that produced it, a sync timestamp, and an explicit null/status when a source didn't resolve, so nothing is fabricated.
Enables MCP clients to query a Twingate network in read-only fashion for users, groups, resources, remote networks, connectors, devices, and access relationships.
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 agents to query Oracle WebLogic Server runtime state, health, and JVM metrics through the REST management API, and to start, shut down, or force-shut-down servers via Node Manager, all under a least-privilege account with allowlisting, read-only mode, and JSON audit logging for every call.
Enables Claude to run safe, read-only diagnostics against servers and websites — certificate chains and expiry, HTTP status/redirects/security headers, DNS records, email authentication (SPF, DKIM, DMARC, MTA-STS, TLS-RPT) and sitemaps. Every check returns severity-tagged findings with concrete fixes, plus a 0-100 score and A-F grade, without any ability to modify the target.
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 Nginx Proxy Manager: manage proxy hosts, redirections, streams, Let's Encrypt certificates, and access lists, with dry-run previews on every change and a one-shot HTTPS host workflow.