"How to run desktop commands on a computer" matching MCP servers:

Enables read-only inspection and diagnosis of Windows, macOS, and Linux machines through eight diagnostic tools covering system profiles, baselines, disk health, startup audits, driver context, and upgrade planning, with voice summaries and a web simulator. It enforces an R0-R3 risk model in code so only safe R0 evidence collection is automatic while riskier actions remain manual guidance.

Hosted remote MCP server for issuing run receipts, summarizing agent changes, checking test evidence, flagging review risks, and exporting run logs for Antigravity agents.

An instrumented MCP server for debugging lost tool calls in Claude Desktop, using ping, echo, sized_echo, and slow_echo tools to record and analyze the full protocol flow.

MCP server that diagnoses ML model regressions by correlating drift reports, eval runs, and deploy logs, providing evidence-cited incident reports through a set of investigation tools.

An MCP server that provides cost and reliability observability for LLM and agent workflows. It records model calls and allows querying and aggregating telemetry data through MCP tools.

Fetches Langfuse observability traces directly into a VS Code coding agent's context, enabling querying and viewing trace data through natural language.

Enables AI agents to monitor Docker containers, system resources, ports, and logs in real-time.

MCP server for On-Call Health burnout analysis. Connects AI assistants to your on-call data for workload insights.

MCP server for managing Ubuntu servers over SSH. Enables Claude to check system health, inspect services, tail logs, review updates, and run commands remotely.

A locally-hosted MCP (Model Context Protocol) server that gives Claude real tools to debug Docker containers — fetch logs, inspect memory/CPU, and run diagnostic commands inside a container, all from a chat with Claude Desktop.

MCP server exposing qbit_manage's Web API as tools, so an LLM can read and manage a qbit_manage instance: run maintenance commands on qBittorrent torrents, manage config files, scheduler, logs, security settings, and system state.

Lets you use Claude Desktop, or any MCP Client, to use natural language to accomplish things on your Cloudflare account.

Enterprise AI operator evaluation MCP server. 27 tools (22 read + 5 write) for measuring, benchmarking, diagnosing, and interv ening on how human operators use AI tools across 5 canonical metrics.

Checks what local coding agents such as Claude Code, Codex and Cursor really did: files changed, commands run and test results read from test output, not the agent's word. Unclear test results can be double-checked by Laya (on your computer) or TypeSafe's Jev (cloud, your own API key). Read-only.

Ask your AI agent about your MCP servers: which tools fail, how a release compares, what clients look for and do not find. Reads from mcpspan with a read token.

MCP server for Keenetic routers that runs on the router itself via Entware: clients, DHCP, Wi-Fi, VPN, logs, port forwarding and DNS records, with dry-run by default on every write. A background watcher calls out from the router when a log or config rule matches.

MCP server for Uptimepage uptime monitoring. An LLM client can read your monitors and incidents, run a check on demand, and post incident updates. Writes need an OAuth login and a scoped token, and each one is logged.

Enables an MCP-capable agent to operate a heterogeneous cluster of Debian/Armbian Linux nodes over SSH from a single inventory, inspecting status and logs, managing packages, services, files, storage and NFS, and deploying new capabilities to nodes through installable modules. Built-in cluster tools fan out to nodes by explicit names, roles or tags with bounded concurrency, while modules can be installed on compatible nodes and run on demand or as systemd services.

Lets AI agents diagnose and debug live Java applications by auto-discovering JVMs and attaching Arthas to run diagnostic commands like thread, trace, watch, and ognl.

Read-only MCP server for TrueNAS Scale debugging, providing k3s tools for kubectl operations and whitelisted midclt calls for system info, apps, and pools.

Enables comprehensive integration with Azure AI services including OpenAI, Cognitive Services, Computer Vision, and Face API through a mission-critical MCP server. Provides enterprise-grade reliability with high availability, observability, chaos engineering, and secure multi-region deployment capabilities.

Enables an AI assistant to diagnose a broken application on a local Kubernetes cluster by inspecting pods, events, and logs, with server-side guardrails, least-privilege RBAC, and an audit log. It can also restart deployments in allowed namespaces only after a dry-run preview and host approval.

Enables grading a website's security headers with per-gap fixes and a README badge, and analyzing logs, code, configs or suspicious messages to determine what happened, how severe it is, and what to fix first. Requests are masked for sensitive data and automatically retried across multiple AI providers when one refuses, subject to a defensive-use-only policy.

Enables AI agents to read protected computers and their check-ins, computer groups, approval requests, the unified audit log, and child organizations through a zero-trust endpoint security portal API. Every operation is read-only, with credentials supplied per request as headers and never stored.

Remote MCP server that gives LLMs access to run network commands

Enables Codex users to check MCP connectivity and inspect recent Computer Use call records, paired hook events, and missing or conflicting observations for reliable app and window targeting.

Enables MCP clients to observe a remote Hermes deployment's agents, sessions, crons, skills, and tools, and to run one-shot remote agent chats via a chat tool.

Analyzes how search engines and AI systems discover, crawl, cite, and convert traffic via CLI and MCP tools.

Enables assistants to securely work on a Chest via personal access token: reading tool logs, builds, and databases, editing rows and variables, and installing or linking tools, with every write requiring a dry run and human confirmation.

Enables Claude Desktop to connect to a ServiceNow instance for debugging and monitoring through natural conversation.