"A calculation query multiplying 198766 by 667891" matching MCP servers:

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.

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

Exposes Creatio CLI (CLIO) commands as tools for AI agents to manage Creatio environments. It enables users to perform environment health checks, restart web applications, and execute raw CLI commands through a stateless HTTP transport.

Enables AI agents on macOS to retrieve current battery levels and charging status for AirPods, iPhone, mice, headphones and speakers tracked by AirBattery, optionally filtering by device or including Nearcast devices. It exposes a single read-only MCP tool over stdio for compatible clients such as Codex and Claude.

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.

Exposes the official lark-cli as an MCP server, enabling agents to execute arbitrary CLI commands, query API schemas, and manage authentication.

Offline server that explains any shell command token-by-token and flags destructive ones (rm -rf /, curl | sudo bash, dd/mkfs/shred to a disk device, chmod -R 777 /) — a safety gate for agentic shell execution.

Universal Docker MCP server for AI assistants (Cursor, Claude Desktop). Manage Docker containers, execute commands, query databases, and handle environment configurations — all through natural language.

A minimal MCP server that exposes a single tool to query local hardware information (OS, CPU, memory, architecture).

Runs commands on machines you cannot SSH into by publishing steps to a transport the far side already reaches (git, file share, S3, relay), then reads back a log with every line timestamped in UTC. Seven tools cover send, status, logs, stall detection and a pre-flight check.

Orchestrates multiple Slidev presentations by managing dev servers and proxying Slidev's MCP tools for targeted presentations.

Enables AI assistants like Claude to query and interact with Rocket Universe and UniData MultiValue databases using natural language.

Enables MCP-compatible coding agents to debug applications using runtime log data, by providing tools to start a local log-ingestion server, track debugging sessions and hypotheses, and correlate logs to specific executions.

Enables operating a FiveM server by sending commands to the FXServer console through txAdmin and returning the console output, with tools for status, players, and server control.

Enables AI agents to autonomously navigate a codebase by listing directories, reading files, searching code, and running whitelisted commands.

Enables AI assistants to control Mac sleep settings by preventing sleep for configurable durations and modes using natural language commands.

A local-first secrets vault for MCP clients that lets AI assistants use secrets by injecting them into child processes, without the plaintext ever entering the model's context.

MCP server that enables AI assistants to debug IoT modules by sending AT commands over serial ports, with a built-in knowledge base for chip platform commands.