"Information or resources about remote work or remote access" matching MCP servers:

Vision-capable MCP server for controlling Amazon Fire TV through Home Assistant, providing screenshot-guided observation, remote commands, and app/URI actions via authenticated REST calls.

Enables reading and configuring an Unfolded Circle Remote Two or Remote 3 through the official Core REST API, exposing activities, touchscreen pages, profiles, integration entities, and physical-button mappings to MCP clients.

MCP server giving AI agents full SSH access with persistent sessions, structured command output, SFTP file transfer, and port forwarding.

Manage local/SSH/WinRM remote hosts via MCP, providing tools for exec, filesystem, screen, process, serial console, and configuration.

Enables AI clients to read and edit a self-hosted wiki as each member’s own account, with mandatory OAuth 2.1 or bearer-token authentication, scoped write/delete permissions, encrypted pre-change snapshots, and safe page/comment operations.

Enables LLM coding agents to inspect, control, and verify remote ROS2 robotics applications without a local ROS2 installation, supporting topics, services, actions, parameters, TF transforms, and automated test suites.

Enables natural language interaction with Unfolded Circle Remote 3/Remote Two for configuration, button mapping, UI editing, and backup/restore.

Persistent SSH sessions for AI assistants, enabling long-running remote shell connections with features like file transfer, port forwarding, and swarm mode.

Enables read-only extraction of LinkedIn profile data via MCP tools, using a local browser bridge for secure, authenticated access without exposing browser credentials.

Enables AI agents to rent cars and manage a Sketchy Rides fleet via MCP, with public read-only tools and OAuth-gated operator tools.

Automates ENVI Classic remote sensing experiments on Windows by executing steps, capturing authentic screenshots, and generating formatted Word/PDF lab reports.

Enables AI agents to monitor MetaTrader 5 accounts on remote Windows VPS via SSH, providing read-only access to positions, history, and logs without executing trades.

An MCP server that enables AI assistants to control TVs on a local network through natural language commands. It currently supports Roku devices, allowing users to launch apps, manage playback, and navigate menus.

A remote MCP image generation server that unifies OpenAI Images and Gemini generateContent APIs with preset-based configuration for multi-provider support.

A template and demonstration project for building, testing, and deploying remote MCP servers using FastMCP and uv. It provides a foundational structure for creating MCP-compliant tools that can be hosted publicly and integrated with LLM agents.

An MCP (Model Context Protocol) server that gives AI agents live, structured ad intelligence across Facebook, Google, and Instagram — data that no base model can produce from training alone. Powered by Apify actors. Works with any MCP-compatible client: Cursor, Claude, etc.

Enables AI apps to securely read, search, organize, draft, attach files to, and send email across up to five self-hosted IMAP/SMTP mailboxes, with sending only after explicit user approval.

Enables MCP clients to read, search, and manage a Yahoo Mail mailbox over IMAP and send or forward messages over SMTP, with multiple accounts selectable per call and writes defaulting to drafts, trash, or dry-runs until explicitly confirmed.

Controls a running Chrome/Chromium browser via the Chrome DevTools Protocol, enabling navigation, JavaScript evaluation, tab management, and raw CDP commands through MCP tools.

Scans a repository for maintenance toil (flaky tests, expiring certificates, TODO rot, dead flags, etc.) and returns a prioritized queue with a credit ledger to track who cleared what.

A remote MCP server for expense tracking, providing tools to add, list, update, delete expenses, and generate summaries, budget status, and monthly trends.

Enables MCP clients such as Claude to query Fitbit and Pixel Watch health data — sleep, steps, heart rate, HRV, workouts, weight and nutrition — through the Google Health API, with built-in OAuth 2.0 sign-in and multi-user access so it can be hosted remotely and reached from web, desktop and mobile.

MCP server that demonstrates the Resources feature by exposing static and dynamic resources, including contact data and personalized greetings, through MCP.

Enables agents to search and deduplicate UK job vacancies across multiple boards, match them against local CVs, and submit complete applications through an automated browser with persistent logins and application memory.

Connects AI assistants and agents to Obsidian vaults through strongly typed tools and resources for reading, creating, searching, organizing, and analyzing notes, tasks, properties, tags, and knowledge-graph data. Supports secure remote access via stdio or Streamable HTTP/SSE with bearer authentication and path isolation.

Enables users to run remote commands, inspect projects, transfer files, and execute scripts on authorized Linux servers through natural-language tool calls. It supports listing servers and groups, executing commands individually or across groups, and uploading or downloading files over secure connections.

Provides full access to a local Windows computer via MCP, enabling arbitrary command execution, file operations, and process management through a secure stdio or HTTP tunnel.

A community MCP server for Cisco Secure Access that exposes the Secure Access REST API to AI clients as a curated catalog of tools for Admin, Deployments, Investigate, Policies, and Reports.

Identifies plants from photos and determines whether a species is native, introduced, or invasive in a given country, drawing on GBIF, GRIIS, and GISD data, and also provides management recommendations and country alien-species lists.

Enables Claude Code sessions to control a Rigol DS1054Z oscilloscope over USB, reading identity, settings, measurements, screenshots and waveforms, and applying undoable or destructive changes such as channel, timebase, trigger and acquisition configuration, run control, autoscale and reset. Tool calls come with read-only and destructive hints so safe operations can be auto-approved while risky ones stay behind user approval.