Use readygpu in your AI assistant

Claude (claude.ai and Claude Desktop)

Works on Free, Pro, Max, Team and Enterprise plans. Free allows one custom connector. On Team and Enterprise, an owner adds it for the organisation first.

1. Open Customize › Connectors.
2. Click + Add, then Add custom connector.
3. Name it readygpu, paste https://readygpu.com/api/mcp as the remote MCP server URL and click Continue.
4. Review the detected settings and click Continue. Under Authentication, choose No sign in, then click Add.
5. In a chat, click + at the lower left, open Connectors and switch readygpu on.

On Team and Enterprise plans an owner adds it under Organization settings › Connectors (Add, then Custom › Web). Members then find it under Customize › Connectors and click Connect.

Official guide: Claude Help Center: custom connectors

Claude Code

Run this in a terminal:

claude mcp add --transport http readygpu https://readygpu.com/api/mcp

That adds it to the current project. Add --scope user to have it in every project. Check it with claude mcp list, or /mcp inside Claude Code.

Official guide: Claude Code docs: MCP

ChatGPT

OpenAI offers custom MCP servers on ChatGPT Business, Enterprise and Edu, on the web only (not the mobile apps). On Business only admins and owners can add one; on Enterprise and Edu, admins can allow other members.

1. Go to chatgpt.com/plugins, click the + button and choose Add custom MCP server.
2. Name it readygpu, enter https://readygpu.com/api/mcp as the Server URL and choose No authentication.
3. Review the warning, tick I understand and want to continue, then click Create as a plugin.
4. Open the new plugin in your plugins and click + to install it.
5. In a new chat, type @ in the prompt box and pick readygpu.

Official guides: OpenAI: add a custom MCP server · OpenAI Help Center: plans and permissions

Cursor

Add this to ~/.cursor/mcp.json to have it in every project, or to .cursor/mcp.json in one project:

{
  "mcpServers": {
    "readygpu": {
      "url": "https://readygpu.com/api/mcp"
    }
  }
}

Turn it on or off under Customize in the sidebar. Cursor asks before it runs each tool unless you allow it.

Official guide: Cursor docs: MCP

VS Code (GitHub Copilot)

Works on every Copilot plan, Free included. With Copilot Business or Enterprise, your organisation's MCP servers in Copilot policy must be on; it is off by default.

1. Open the Command Palette and run MCP: Add Server.
2. Choose HTTP, paste https://readygpu.com/api/mcp, and enter readygpu as the server ID.
3. When asked where to save it, choose Copilot Global to have it in every workspace.
4. In Copilot Chat, click Configure Tools to check readygpu's tools are on. If VS Code asks whether you trust the server, confirm.

Or add it to the file yourself:

{
  "mcpServers": {
    "readygpu": {
      "type": "http",
      "url": "https://readygpu.com/api/mcp"
    }
  }
}

In .vscode/mcp.json, or the profile's mcp.json (MCP: Open User Configuration), the top-level key is servers instead of mcpServers.

Official guides: VS Code docs: MCP servers · GitHub docs: MCP in Copilot

Devin Desktop (formerly Windsurf)

Windsurf became Devin Desktop in June 2026. Its default agent, Devin Local, reads MCP servers from ~/.config/devin/mcp_config.json (%APPDATA%\devin\mcp_config.json on Windows):

{
  "mcpServers": {
    "readygpu": {
      "url": "https://readygpu.com/api/mcp",
      "transport": "http"
    }
  }
}

With Devin CLI installed, devin mcp add -s user readygpu https://readygpu.com/api/mcp adds it for you. Devin Local asks before each tool call; you can allow readygpu's tools for the session or for good. The older Cascade agent takes serverUrl in place of url.

Official guides: Devin docs: MCP configuration · Devin docs: Devin Local · Devin docs: Cascade MCP

Gemini CLI

Run this in a terminal:

gemini mcp add --transport http --scope user readygpu https://readygpu.com/api/mcp

Without --scope user it goes in the current project's .gemini/settings.json. To edit the file yourself, use httpUrl: in Gemini CLI, url means an SSE server.

{
  "mcpServers": {
    "readygpu": {
      "httpUrl": "https://readygpu.com/api/mcp"
    }
  }
}

Check it with /mcp inside Gemini CLI.

Official guide: Gemini CLI docs: MCP servers

OpenAI Codex

Run this in a terminal:

codex mcp add readygpu --url https://readygpu.com/api/mcp

Or add it to ~/.codex/config.toml:

[mcp_servers.readygpu]
url = "https://readygpu.com/api/mcp"

The Codex CLI, the Codex IDE extension and the ChatGPT desktop app share this configuration. Check it with codex mcp list, or /mcp in the Codex terminal UI.

Official guide: OpenAI docs: Codex and MCP

Any other MCP client

• Server URL: https://readygpu.com/api/mcp
• Transport: Streamable HTTP (often labelled HTTP or streamable-http). There is no SSE stream and no session.
• Authentication: none. No key, token or header.
• Tools: 6, all read-only.

A client that can only start local (stdio) servers, or only speaks the older SSE transport, cannot connect to it directly.