"Shell" matching MCP servers:

Gives AI agents shell access by providing a run_command tool for executing shell commands and returning stdout, stderr, and exit code.

Enables AI agents to compose MCP tool calls into Unix-style pipelines, executing complex workflows server-side and returning only the final result.

MCP server that protects shell, file, database, git, and HTTP operations with per-agent permission rules

A cooperative guardrail for AI agents that blocks destructive shell commands, SQL statements, or cloud operations until a human approves them out-of-band, with a tamper-evident local ledger.

Local-first operator MCP server: recall across your own sessions, chats and files, an encrypted vault, SSH to your own hosts, and gated shell, browser and device tools. 130 tools over stdio or HTTP; everything runs on your machine — no hosted service, no account, no API key.

MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.

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.

SassyMCP is a comprehensive MCP server that replaces 75+ individual servers with one 34MB executable. It provides 274 tools for file operations, shell, desktop automation, GitHub/Git, Android interaction, network/security auditing, SSH, OCR, and Windows system management.

Exposes CAD design tools (box, cylinder, shell, etc.) via MCP, allowing AI agents and clients like Claude to create and manipulate parametric CAD models in Autodesk Fusion or a simulator.

Lets coding agents query a hosted knowledge graph of a git repository over MCP or the shell to retrieve recorded commit intent, co-change coupling, ranked blast radius, and computed architecture. Answers are drawn from the graph rather than file reads, reporting measured per-answer token savings.

Enables LLM clients to execute shell commands safely through the MCP protocol, with features like session management, safe mode, and process control.

MCP server that evaluates Terraform plans, shell commands, and tool calls to assess recoverability and risk before execution, enabling safe AI agent actions.

Connects MCP-compatible AI clients to an explicitly authorized Windows, macOS, or Linux computer for controlled Machine, Browser, and Desktop execution, including files, shell commands, native apps, and local browser sessions. Also offers a separate hosted Cloud Browser for browser tasks that should run outside the user's own workstation.

Governance engine for MCP tool calls, providing deterministic rule enforcement to block destructive actions like SQL drops, shell commands, and file system modifications before execution.

Enables AI assistants to work with many Android devices over ADB at once, including listing and connecting endpoints, checking device health, installing APKs, and optionally running shell commands in parallel across selected devices.

Policy-enforcing MCP proxy that blocks dangerous tool calls before they execute. Protects credentials, filesystem, shell, and databases across Claude Desktop, Cursor, Windsurf, and OpenClaw.

Gives a compatible coding agent read-only access to bounded local verification of changes inside a single host-chosen workspace, exposing six stdio tools that inspect capabilities, static checks, impact analysis, policy evaluation, evidence generation, and suggested tests without shell access, plugin loading, or repository upload.

Enables an AI agent to set up, run and verify engineering simulations through typed tools — creating or importing cases, setting boundary conditions, running solvers, checking convergence, verifying results against references, and rendering output, with edits appearing live in the GUI. It exposes no shell or code-execution tool.

A local MCP runtime that lets MCP clients such as ChatGPT inspect workspaces, search, read, write, and patch files, manage directories, run shell commands, and control persistent processes on your machine through an outbound Device Relay connection that needs no open inbound port. It can also publish a local loopback OpenAI-compatible model runtime as a Frely personal Provider.

Enables any MCP or shell-capable agent to interact with native ViraStack tasks in Cadence Virtuoso, including selecting sessions, submitting requests, polling jobs, cancelling tasks, and replying to pending questions.