"Open Collective" matching MCP servers:

An MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.

An open MCP server that gives any AI agent SSH access to remote Linux/Unix machines — shell commands, file read/write, and SFTP transfers.

Local MCP server that exposes iTerm2 tab/session logs to MCP-capable agents via AppleScript, enabling tools to list open tabs and retrieve terminal scrollback.

Enables AI coding agents and IDEs to run a complete open-source FPGA flow, including synthesis, place-and-route, bitstream generation, and safe hardware programming for iCE40/ECP5 boards.

An MCP server for driving an ITS session on a PiDP-10 emulator over raw TCP, supporting persistent connections, raw control-byte transmission, and escape syntax for DDT commands. It enables interaction with ITS systems through natural language via MCP tools like open, send, read, and status.

Zero-config SSH/SFTP MCP server that lets an LLM client open temporary SSH/SFTP sessions to remote hosts, run commands, and upload/download files without holding any pre-baked credentials.

A local MCP server that delegates tasks to a subagent runtime via OpenAI-compatible interfaces, enabling file operations, command execution, and rollback of local file changes.

Geniuz stores everything in a local database locally on Mac, Windows, Linux, Raspberry Pi. No cloud. No account. No API keys. Nothing leaves your machine. It's open source; you can read every line of code.

ssh-mcp-pro is a secure Model Context Protocol (MCP) server for SSH automation, enabling clients to open SSH sessions, run commands, manage files, transfer artifacts, create tunnels, and perform package/service operations under policy control.

MCP server that lets AI clients manage a Qinglong (qinglong) panel via natural language, covering crons, environment variables, scripts, subscriptions, logs, configs, and dependencies through its Open API.

MCP server that lets an AI assistant see and control an Android phone over ADB: screenshots, UI dump, tap, swipe, type, keys, open apps. Safety guards: device allowlist, sensitive-app block, raw shell off by default, rate limit.

Provides Claude with direct access to the Open Porous Media (OPM) reservoir simulation stack, enabling running simulations, inspecting results, and automating workflows via natural language.

Enables control of macOS applications through natural language, allowing users to launch apps, execute AppleScript commands, manage running applications, and open files with voice or text commands.

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 command-line AI agents to communicate with a person through seven verbs for telling, asking, showing files, reporting activity or status, reading replies and open questions, and closing questions. It writes the same exchange files as the CLI so applications can present and respond to the conversation on any screen.

Enables voice assistants to start, monitor, message, and approve local Claude Code sessions on your computer, including sessions already open in a terminal. It exposes session management, recaps, approvals, and history search as MCP tools.

A download manager for humans and AI with a native MCP server: add_task, list_tasks, wait_for_task with progress notifications from any MCP host. Multi-threaded multi-mirror HTTP, BT/magnet, 1000+ video sites (yt-dlp), RSS, token-secured remote Web UI. ~8MB, open source.

An MCP server for managing remote SSH servers, enabling AI agents to execute commands, transfer files, and perform deployment operations securely.

Exposes locally installed bim-cli verbs as MCP tools so an AI assistant can extract and stamp PDF text, split or merge PDFs, look up flood zones by address or coordinates, and convert IFC/FBX/glTF files headlessly on Windows without Revit or any desktop app open. All execution stays on the local machine through a stdio server launched from the existing binary.

Enables an AI agent to open a real Konsole window on KDE Plasma 6 / Wayland, type commands directly into its pseudo-terminal, read output and exit codes, send special keys, and manage interactive programs. It also brings that window to the foreground and captures the desktop with the system's own Spectacle, returning the screenshot image in the tool response.

Enables Claude Desktop or Claude Code to inspect, visualize, and process point clouds and meshes in natural language, with tools for metadata, density, subsampling, registration, distance computation, normals, filtering, merging, and format conversion. Tuned for cave, tunnel, and underground 3D surveys, it can run batch command-line operations without requiring an open GUI.

Enables AI agents to interact with real terminal sessions across local and remote hosts, driving multi-turn interactive programs like TUIs, REPLs, and SSH prompts through MCP.

A native MCP server for Unreal Engine 5.7 that lets AI assistants inspect and control an open Unreal Editor through a single 'unreal' tool, supporting Python/console command execution and async tasks.

Connects MCP-compatible AI clients and agents to one durable Project Brain plus controlled access to authorized project folders on your own machine. Enables file editing, terminal and Git operations, project intelligence, browser automation, and local MCP server federation, all scoped to explicit workspace grants.

Enables Claude Desktop's Chat and Cowork — which lack shell access — to drive the ego (lite) browser by launching the ego-browser CLI as a child process and running model-written JavaScript against it. This restores the missing execution layer so users can open pages, work in task spaces, and take snapshots without a CLI agent.

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 controlling an Ubuntu desktop VM over SSH: run shell commands, open real terminal windows, drive the mouse and keyboard, manage windows, transfer files, and capture genuine screenshots of the screen or a single window. Intended for GUI-dependent work such as security experiments, vulnerability reproduction, form filling, and report illustrations.

Enables LLMs to list, open, and close installed software on Windows, macOS, and Linux through natural language.

Operate packet-radio digipeater nodes from Claude and other MCP clients.

Enables AI assistants to autonomously execute over 200 open-source penetration testing tools via MCP, including reconnaissance, web exploitation, and brute-forcing, through a unified server architecture with Docker sandboxing for safe execution.