Skip to content

Cursor SCRIPTMASTERLABS — SML agent-safety prompt-injection

How to: Cursor SCRIPTMASTERLABS — SML agent-safety prompt-injection

client:Cursor transport:streamable-http tool:prompt-injection

Add SCRIPTMASTERLABS — SML agent-safety to Cursor

  1. 01

    Open ~/.cursor/mcp.json and merge this in. Keep any servers already there.

{
  "mcpServers": {
    "agent-safety": {
      "url": "https://sml-agent-products.onrender.com/agent-safety/mcp"
    }
  }
}
  1. 02

    Save the file and restart Cursor.

  2. 03

    Ask for something prompt-injection does. Cursor lists the server's tools on connect and calls prompt-injection itself — you do not invoke it by name.

  3. 04

    If nothing happens, check the server is running and that SCRIPTMASTERLABS — SML agent-safety's identifier in your config matches the one above exactly.

Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs

Same tool, other clients

This list was read from the server itself, by connecting to it and calling tools/list on 11 November 2026. It is what the server actually exposes, not what its listing claims.

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.