"How to run local command-line commands" matching MCP servers:

MCP server that integrates the LINE Messaging API to enable AI agents to send messages and manage LINE Official Accounts.

Your AI agent can't touch Stripe, Gmail, Slack or more, without your tap. mild.run intercepts every sensitive action and sends you a notification to approve or block — before anything executes. Agent never holds credentials.

Enables AI agents to interact with the Execute.run bot API for managing Shell balances, transferring funds, and executing LLM requests. It provides tools for identity verification, transaction tracking, and performing compute tasks through the Execute.run platform.

MCP server for managing Markdown-Driven Task Management (MDTM) files with task, parent task, environment, and workflow management, enabling structured development workflows.

Enables MCP-compatible AI agents to deploy applications to Google Cloud Run by providing tools for deploying code, listing services, and managing Google Cloud projects.

MCP server exposing a parametric policy engine for evaluating, simulating, and managing rules, with dynamic plugin support for domain-specific calculations.

Enables secure execution of Python code in a sandboxed WebAssembly environment using Pyodide and Deno. Automatically handles package management and captures complete execution results including stdout, stderr, and return values.

Enables AI assistants to query PostgreSQL, MySQL, SQL Server, Oracle, and MongoDB databases through MCP with read-only, audited access.

Provides access to Upvote.club public API via stdio, enabling task creation, status checking, platform listing, and API reference queries.

Unified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.

Publishes static sites to Drop2Run from an AI agent: hand it files written in the chat or a folder on disk, and it returns a live HTTPS URL. Six tools — publish_files, publish_dir, list_sites, delete_site, and login / login_code — with no git, no build step and no repository.

A fail-closed MCP server for Msty Studio on macOS that provides read-only diagnostics and an optional bounded local-generation tool, without accessing chats, keys, or configuration.

Generates, validates, and deploys CrowdSec WAF rules and scenarios through natural language.

Enables MCP-compatible agents to execute bash and subprocess commands through a zero-dependency sandbox guard that blocks destructive system mutations, path traversals, reverse shells, and other unsafe execution patterns.

Exposes the full Gate API v4 to MCP clients with 384 tools for spot, futures, margin, wallet, and more. Supports both public endpoints (no auth) and authenticated trading operations.

This MCP server lets AI agents connect to Figma to read, analyze, create, and modify designs, including elements, styles, assets, and code generation. It works with free Figma accounts and supports parallel multi-agent use across MCP-compatible clients.

Enables AI agents to sign Geode blockchain transactions on the user's own machine, with keys that never leave it, by independently decoding and verifying each server-prepared transaction before approving it. Refuses anything outside allowed Geode app actions or beyond the configured per-transaction, daily, and storage-deposit GEODE limits.

Enables AeyeStudio AI chat to securely access and control local PC resources such as files, Excel, clipboard, apps, and shell through a localhost MCP agent with user approval.

Enables Claude Desktop to access and manage Geniads' skill library by calling the platform's REST API directly from the local machine, bypassing the hosted MCP connector.

Model Context Protocol server to run Python code in a sandbox.