"Techniques to Improve Agent Programming" matching MCP servers:

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.

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 management of capture sessions, rules, certificates, and protocol communication through an MCP endpoint, controlling a sing-box core.

Enables AI apps to inspect and manage a NextDNS account in plain language — profiles, analytics, query logs, blocklists, security and parental control settings — with every change saved and reversible via undo. It runs self-hosted on your own computer or server, keeps per-profile read/write/hidden permissions, and requires double confirmation for deletions or overwrites.

Enables a single MCP client to connect to many upstream MCP servers through one gateway, with prefix-based routing, health checks, circuit-breaker failover, and unified stdio/HTTP access.

Provides 9 utility APIs for AI agents covering DNS, email, IP, QR, WHOIS, URL health, headers, text extraction, and tech detection, with x402 micropayments on Base.

An MCP server for managing home lab VMs and PNETLab topologies, enabling AI agents to power VMs, handle snapshots, and verify device configurations with explicit allowlists and confirmation gating.

Enables DevOps Agent to troubleshoot VPC networking problems by running live probes (dig, nc, ping, traceroute) via SSM and querying VPC Flow Logs via Athena.

Exposes network-monitoring tools (query metrics, analyze windows, compare, logs, status, runbooks, speed tests) as an MCP server for agentic workflows. Designed with evaluation suites, cost-aware model routing, and semantic tool retrieval.

Enables agents to call paid utilities for DNS/SSL checks, site status, summarization, keyphrase extraction, decision advice, data cleanup, claim verification, and grounding via per-call USDC payments over x402, with free discovery tools and no signup or API key.

A read-only MCP server exposing GPON access-network tools for inventory, status, configuration diff, and alarms, enabling a LangGraph agent to audit ONT provisioning against a golden baseline. It runs against a simulated network and enforces read-only constraints at multiple levels.

NexaLayer MCP Server — a Model Context Protocol server that lets AI agents create and manage dynamic and static proxy sessions with budget guardrails.

Buy and manage domain names with USDC via API. Search availability, register .com/.ai/.io domains, and manage DNS records. Designed for autonomous AI agents. 15% referral commissions.

A safety-first MCP server for managing UniFi networks, exposing 17 tools for telemetry, diagnostics, and guarded mutations with dry-run previews and confirm requirements.

Enables AI agents to run eleven read-only network checks — interfaces, Wi-Fi signal, IP configuration, ping, traceroute, routing and ARP tables, DNS, port and HTTP probes — and to diagnose faults bottom-up across the network layers, returning the first broken layer with a plain-English explanation and fix.

An MCP server that exposes a growing catalog of Fortinet VISTA tools to partner agents for FortiOS/FortiGate engineering and support, starting with log analysis and visualization.

Provides read-only SSH access to network devices (routers, switches, firewalls) with command allow/deny policies, nt-templates output parsing, and an audit trail, enabling an AI agent to query device state securely.

MCP (Model Context Protocol) server for rustunnel. Lets AI agents (Claude Code, Cursor, Windsurf) create and manage public tunnels to local services from inside an agent session.

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.

Uptime monitoring from your AI agent: create and diagnose checks (40 types: HTTP, TCP, DNS, SSL, ICMP, databases, message queues and more), read results and incidents, and manage status pages and maintenance windows. Built into the self-hostable SolidPing server, served over streamable HTTP at /api/v1/mcp.