"Shell" matching MCP servers:

Takes a plain-language automation goal and returns a recommended tool stack, command, validation checks, recovery guidance, and a machine-readable package contract for agents and builders.

MCP server that lets Claude Code drive the local Codex CLI as a sub-agent for concurrent queries and optional file/shell actions, using the CLI's existing login and sessions.

Provides a workspace-safe, read-only bridge between browser-based AI planning/review and local coding agents, enabling structured plan, execution summary, and review handoffs without granting shell, file write, or Git push access.

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.

Enables MCP clients to retrieve Telegram setup plans, normalize task briefs, and run health diagnostics locally without exposing shell access or stored credentials.

Enables web-based AI clients like Claude, ChatGPT, and Grok to securely operate a local machine through OAuth-gated MCP tools covering files, shell, Git, databases, browser automation, and background tasks.

Enables ChatGPT to supervise and control local Codex runtime sessions through a secure MCP interface, managing threads, turns, approvals, events, and recovery without exposing direct file, shell, Git, SSH, or model loop access.

Enables Cursor agents to route subagent tasks and gate reads, writes, and shell commands through fast TypeSafe Jev judgments, exposing tools for choice, scoring, and noul decisions.

A passive MCP server that exposes a toolbox of executable tools (shell, network, HTTP, AI search, SSH, S3 file operations) to autonomous agents via Streamable HTTP, with strong security features including Docker sandboxing and WAF.

Gives a coding agent its own persistent, authenticated Linux desktop over MCP, so it can browse signed-in sites, run shell commands, move files, and paste credentials that the model never sees, with logins surviving between tasks and human takeover available at any time.

Serves a local dsh workspace as a protected Streamable HTTP MCP endpoint, letting authenticated web AI agents read, search, patch, inspect, and operate the project, with optional shell commands, LSP support, and public tunneling.

Enables local/remote execution infrastructure through the official Codex Runtime, providing shell, files, Git, sessions, browser, computer use, recoverable tasks, multi-host routing, dynamic MCP integration, and skill lifecycle management.

MCP server that bridges Claude Code to Google Antigravity's CLI, enabling Claude to orchestrate Gemini workers in parallel for reading, writing, verifying, and autonomous tasks. It provides tools for single dispatch, parallel fan-out, background jobs, and handles permission, cwd, and shell pitfalls.

Runs isolated AI agents in Docker containers with persistent workspaces and conversation history. Each agent has access to file operations, shell commands, GitHub integration, and can connect to external MCP servers for additional tools.

Enables ESP32 XiaoZhi voice devices to command a Windows PC via MCP, including app control, file operations, screen vision, browser interaction, shell execution, and orchestration of local AI coding agents like Codex CLI and Claude Code.

Give AI agents Zero-Trust access to production infrastructure without the risks of granting them shell access. Actions are bounded by policy and an on-host runner.

An MCP server that enables AI agents to execute real-world actions through 10 specialized engines covering authenticated API calls, browser automation, visual QA, shell commands, file operations, job scraping, and parallel task execution.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

MCP server for local-first agent handoff: enables AI sessions to publish curated context, list/read updates, route handoffs to specialists, and advance per-consumer cursors, with SQLite persistence and no shell or network access.

jobd is a self-hostable, GPU-aware job broker that queues and routes shell commands across your own machines — picking workers by available VRAM and tool tags, streaming logs back, and surviving across sessions. It ships native MCP integration, so agents can submit, monitor, and control long-running or GPU jobs as tools.