How do I connect Open Compute MCP Server to Claude?

The project does not publish a launch command that MCPVault could verify. Open the repository linked on this page for its install steps; the listing names Claude Code, Cursor as compatible clients.

Is Open Compute MCP Server free?

The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.

What can Open Compute MCP Server do?

Open Compute MCP Server documents 16 tools to the agent, including capture, chat, click_name. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.

Open Compute MCP

Unclaimed

by ellmos-ai

npm launcher for the open-compute MCP server: model-agnostic computer-use (screenshot, safety-gated actions, Windows UIA) over MCP; spawns the Python open-compute server from GitHub.

Set up this server

Compare servers My Stack

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions

ai-toolsautomationcomputer-usegui-automationlocal-firstmcpmcp-servermodel-context-protocolnodejsnpm-packageuiawindows

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

16 of 16 tools

Documented tools (16)

From project documentation. A server handshake does not verify each tool’s description or behavior.

capture

Screenshot the screen → returned as an image (optionally a single window).

chat

Human→model message about screen content, optionally with screenshot.

click_name

Resolve an element by name and click it.

do

Execute one canonical action or a batch (click/type/key/scroll/drag/hold/…).

get_screen_size

Virtual-desktop geometry + per-monitor breakdown (read-only).

invoke

Click-free activation of an element via UIA patterns.

list_windows

List open windows with exact titles, rects and normalized centers (read-only).

push_status

Feed-manager status (read-only).

rec_replay

Replay a .clirec macro (needs the optional clirec package).

signal_abort

Ask the human for a short abort reason; the message is returned for the model.

signal_hide

Hide the signal overlay.

signal_show

Show the screen-usage signal overlay: glowing border + cursor ring colored per mode (control=red, observe=blue, …); persists in the server process.

signal_status

Overlay state + collect a pending abort-hotkey message (consumed on read).

talk

Push-to-talk voice note → WAV path (hold key, speak, release; STT/TTS model-side).

tree

List UI elements via Windows UIA (name/role/centernorm).

watch_dir

Watch directories for file-system changes.

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Open Compute MCP Server

How do I connect Open Compute MCP Server to Claude?: The project does not publish a launch command that MCPVault could verify. Open the repository linked on this page for its install steps; the listing names Claude Code, Cursor as compatible clients.
Is Open Compute MCP Server free?: The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Open Compute MCP Server do?: Open Compute MCP Server documents 16 tools to the agent, including capture, chat, click_name. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.