"Using Claude in Cursor to Run and Read Outputs from PowerShell or Terminal" matching MCP servers:

A lightweight MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI - saving context window and tokens for what matters.

Enables Cursor AI to read and modify Figma designs programmatically via the Model Context Protocol.

MCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.

Enables management of visible, interactive terminal sessions across platforms (macOS, Windows, Linux, WSL). Supports creating, executing commands, capturing output, and managing multiple terminal windows simultaneously.

Unofficial Powershell MCP server

Enables automatic collection and AI analysis of Slack messages to create organized Notion pages, supporting custom analysis directions like meeting minutes, issue extraction, and topic classification.

Enables Claude Desktop and other AI tools to interact directly with Figma, allowing for powerful AI-assisted design capabilities through natural language commands.

MCP server that converts file contents into compact, line-numbered PNG images for vision models to read, reducing token usage by roughly 7x for large files.

Enables progress-triggered text-to-speech in Cursor Agent, with speak and stop controls and voice matching the system UI language.

A FastMCP server for Cursor platform APIs enabling spend guardrails, cloud agent monitoring, and inter-agent inbox messaging.

Lets ChatGPT, Claude Desktop, Claude Code, and other MCP clients run an allowlisted set of local commands and read files from a chosen directory, so an assistant can analyse a codebase or trigger local generators (images, sprites, assets) without metered API tokens. The server is read-only and deny-by-default by default, with no shell, path containment, opt-in writes, and required auth when exposed over HTTP.

An MCP server for creating and managing shared terminal progress bars from AI agents, enabling real-time tracking of parallel tasks.

Enables AI agents to open persistent interactive terminal sessions with network devices over SSH, Telnet, TCP console, or serial, write raw commands including nested ssh/telnet transitions, and read full output without requiring a particular prompt format. It supports multiple concurrent sessions and keeps credentials/secrets out of MCP arguments or audit logs.

Enables interactive feedback with image support in Cursor, allowing users to paste images for visual context and feedback.

A local MCP server that lets LLM agents read EPUB books and PDF documents with outline-first navigation, precise node reads, and local SQLite persistence.

Enables MCP clients to observe and, when explicitly enabled, send constrained input to whitelisted tmux sessions, with support for local STDIO and loopback-only HTTP transport behind an authenticated tunnel.

Enables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.

Local + remote terminal interaction control MCP Server. Lets AI agents control interactive TUI programs the way a human would.

An MCP server that gives Jan AI terminal and code execution capabilities, enabling shell commands, multi-language code execution, file manipulation, and git operations locally.

Enables academic research through paper search across multiple databases (IACR, CryptoBib, Crossref, Google Scholar), PDF processing, and GitHub repository browsing. Features modular architecture with FastMCP-based proxy server routing to specialized academic tools.