MCP servers · barhamagha1

Bridge MCP: MCP server for AI control of a Windows PC

An MCP server that lets an AI client launch apps, send mouse and keyboard input, take screenshots and run commands on a Windows PC.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Bridge MCP is a Model Context Protocol server that gives an AI client control over a Windows PC. It provides about 40 tools in groups: app control (launch, switch, resize, close), mouse and keyboard input, screen capture and UI element detection, Chrome and Playwright browser automation, PowerShell, CMD and file operations, and clipboard handling. It has two parts: bridge_mcp.py, the MCP server, and local_agent.py, an HTTP agent on the PC that runs the commands. Agent registrations and the last 100 commands are kept across restarts.

It suits cases where an AI needs to operate desktop applications, read what is on screen, or drive a browser on a Windows machine. A web dashboard shows a live stream of the desktop with detected elements highlighted, and lists pending requests.

To run it, start local_agent.py in a terminal and keep that window open; the agent registers itself with the server. Then add Bridge MCP to an MCP-compatible client such as Claude Desktop, Cursor or VS Code. Playwright browsers install on first use. Dangerous commands, such as writing files or running shell scripts, are blocked by default and must be approved from the overlay or the dashboard.

Limitations and requirements

The local agent must be running for the AI to control the PC. Dangerous commands are blocked by default until approved. Choosing ALWAYS APPROVE turns off Safe Mode and approves future commands. Playwright browsers (about 100MB) download on first use. Requests use Bearer tokens generated automatically and saved in agents.json. The features are described for Windows, and the setup requires editing the MCP client configuration.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Bridge MCP

    Visual Desktop Bridge - Give any AI full control over Windows to automate apps and inputs.

    v2.1.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
modelcontextprotocol

MCP reference servers

Seven small example servers maintained by the Model Context Protocol project: files, Git, web fetching, memory, time, step-by-step thinking and a test server.

92K GitHub starsSoftware development
Updated 17 Nov 2026