"Writing about MCP" matching MCP servers:

Enables LLMs to communicate with hardware devices via serial ports. Provides tools for listing ports, opening/closing connections, reading/writing data, and controlling serial signals.

Enables a coding agent to get short, token-efficient answers about a project through grouped searches, focused symbol or section reads, and bounded read-only script output, with safety limits on paths, secrets, commands, and response size.

Enables creating temporary Quarto projects, writing files into them, rendering documents, and inspecting project output over MCP, while managing reusable metadata defaults.

Enables AI agents to safely access and administer remote machines over SSH using existing OpenSSH config, with typed tools for running commands, reading and writing files, listing directories, and retrieving file metadata.

An MCP server that lets AI assistants inspect and control Asterisk and FreeSWITCH PBX systems, enabling natural language queries about live switch status, channels, registrations, and call control.

Provides AI coding agents with structured, evidence-based diagnostics about the local development environment, detecting tech stack, runtime mismatches, dependency state, services, ports, and Git status without exposing secrets or using network calls.

Enables reading, writing, editing, searching, running commands, transferring files, and using git on a remote Linux server over SSH via MCP tools.

Enables LLMs to securely SSH into remote servers, execute commands, and manage files via SFTP including listing, reading, writing, deleting, and renaming files.

Enables MCP-based communication with existing interactive terminal channels, such as shells or agent CLIs, by listing, reading, writing text, and sending control signals to tmux sessions without creating or managing them.

Enables MCP clients to manage a workspace through file reading, writing, editing, searching, Bash/Python execution, and job control, with optional desktop GUI and Cloudflare Tunnel access.

Enables users to interact with container registries through the ORAS CLI, providing information about container images, platforms, and signatures via natural language queries.

An MCP server that exposes RS232 serial port connectivity, enabling listing, opening, reading, and writing to serial ports via tools and resources.

Provides local desktop agents with durable project memory and safety gates for writing long novels, enabling continuity management, chapter drafting, and state-aware handoffs.

An educational MCP server exposing shell command execution (PowerShell and sh) and a benign tool for learning about MCP tools, resources, and security risks like tool poisoning.

Serial communication and protocol analysis MCP server that gives AI coding assistants direct access to serial ports for reading, writing, decoding, and capturing embedded device output.

Enables AI assistants to access SAP ADT APIs for reading, writing, debugging, deploying, and testing ABAP code through natural language or DSL automation.

A remote Streamable HTTP MCP server that lets web clients like Claude.ai and ChatGPT manage cloud machines with OAuth login — creating, starting, pausing and deleting machines, running commands, reading and writing files, managing snapshots and public ports, and driving an optional Linux desktop via screenshots and input actions. Long-running work can be backgrounded and operations polled, so browser-based clients stay within their timeouts.

Enables ChatGPT Chat to operate an Apple Silicon Mac by running commands, reading and writing files, viewing the screen, driving app UIs, and accessing everyday apps through an OpenAI Secure MCP Tunnel while keeping machine-specific details local.

A transparent message ferry between Claude Desktop and Claude Code CLI, enabling task delegation with any MCP configuration without the bridge needing to know about specific MCPs.

Enables Claude Code to use locally encrypted, multi-tenant credentials by running commands with injected secrets, writing .env files, materializing files, and making HTTP requests, while scrubbing values from all output so they never enter the chat. Also supports sealed retrieval and saving through native dialogs or an auto-clearing clipboard, role-based credential selection, versioning, rollback, archiving, and a full audit log.

Enables AI assistants to automate context-management tasks for the Horizon Worlds editor by executing system commands, reading/writing files, and managing processes.

Bridges AI assistants to seismology software (ObsPy, CWP/SU, SAC, PyGMT), allowing users to process seismic waveforms and perform analysis through natural language instead of writing code.

MCP server for live process memory introspection and debugging on Linux x86_64. Enables reading/writing process memory, searching patterns, ptrace attach/registers, running commands, and valgrind execution.

MCP server wrapping the agy CLI, enabling querying, web search, and file writing through tools like ask-agy, search-web, and write-file.

Enables ChatGPT conversations to drive a paired Windows PC by reading and writing files, running interactive terminals, automating desktop UI, and composing or editing DOCX documents in WordCraft, all through 42 MCP tools. Access is secured with OAuth, device pairing, approved folders, and locally managed permissions for sensitive actions.

Enables DeepSeek Harness to operate files on another computer over MCP, including browsing, reading, writing, editing, searching, moving, and recoverable deletion, with optional command execution. It supports Windows and macOS via LAN or Tailscale with directory authorization and logs.

Drives a SEGGER J-Link probe to debug microcontrollers, enabling firmware flashing, CPU halt/resume/reset/step, and reading or writing memory, peripheral registers and core registers. Also exposes an escape hatch for arbitrary J-Link Commander commands.

Enables ChatGPT or any MCP client to operate safely on a designated workspace by listing, reading, searching, writing, and trashing files, inspecting Git status/log/diff, and optionally running allowlisted executables without a shell.

Enables MCP clients such as Claude Code, Cursor, Codex, and Gemini CLI to use API keys without the model seeing them, by listing project and key names, writing approved .env files, running commands with keys injected, storing keys, creating projects, and importing .env files while returning no secret values.

Enables MCP clients such as ChatGPT and Claude chats to control a Windows desktop by taking screenshots, moving the mouse, typing text and key chords, focusing windows, reading or writing the clipboard, and launching applications. Access is gated by local approval modes, input kill switches, and an optional authenticated relay for remote clients.

Lets MCP clients drive the 13 ArtCraft Crafting Apps through their CLI binaries using five compact tools — app discovery, command lookup, ordered command execution, a verbatim CLI escape hatch, and help text. This replaces the 799 per-app tool schemas (~140k tokens of resident context) with about 900 tokens, while keeping full access to the apps' 7,027 command IDs.

Bridges a locally running OpenChatX Agent Runtime to Anthropic Claude (Free, Pro, and Team) on web and mobile as a spec-compliant OAuth 2.1 Remote MCP endpoint. It grants Claude 26 local agent tools for file reading, writing and patching, regex search, shell and terminal execution, skills and sub-agent dispatch, project and goal management, and cross-session memory.

Dynamically exposes CLI/bash commands as MCP tools and creates structured AI prompt templates through simple YAML configuration files, enabling users to transform any command-line tool into an MCP-compatible interface without writing code.

Enables ChatGPT to work on a local machine through an MCP connection by inspecting projects, editing files, running bounded terminal and Git commands, driving Chrome or Edge, and reading or writing an already-connected Excel workbook. It invokes the Codex model explicitly only when a task genuinely needs it, so ordinary local tool actions consume no Codex model usage.

Gives MCP-compatible AI clients a controlled bridge to local files, processes, search, and document utilities, including reading/writing and moving files, text block editing, directory listing, content search, starting and managing terminal processes, and PDF/Excel/DOCX/image handling. It serves these tools over MCP Streamable HTTP at a configurable endpoint, with optional Bearer-token authentication and read-only or restricted-directory modes for safer remote exposure.

Enables ChatGPT's web interface to operate a real Mac by executing shell commands and reading or writing files over a reverse SSH tunnel, without installing a client or consuming API quota.

Enables an AI client to drive a Raspberry Pi — running shell commands, reading and writing files, and installing packages — by relaying encrypted jobs through the PNA Vercel API, which only ever stores opaque blobs. Each call takes the Pi's api_key and session_key, encrypts locally, long-polls for the Pi's decrypted response, and returns the result, with no secrets logged.

Cross-platform remote debugging agent with MCP support for launching processes, screenshotting, hooking APIs/addresses, and reading/writing memory via Frida.

Enables AI tools like Claude to interact with a remote machine's file system and shell via a secure HTTPS endpoint. It provides standardized tools for executing shell commands, reading and writing files, and navigating directories.

A terminal emulator MCP server specifically engineered for LLMs with block-oriented design that organizes command input/output into recognizable blocks and semantic session management. Enables AI to efficiently use terminals for writing code, installing software, and executing commands without context overflow.