Hyperbrowser MCP Server for Cursor: Setup & Config

What you can do with Hyperbrowser in Cursor

Pick it when an assistant needs both web extraction and a choice of cloud browser agents.

• Extract page content as Markdown or screenshots
• Delegate interactive tasks to cloud browser agents
• Create and manage persistent browser profiles

Before you start: Hyperbrowser in Cursor

• npx
• A Hyperbrowser API key
• An MCP-compatible client

The README supplies client configurations for Cursor, Windsurf, and Claude Desktop. A source checkout can instead be built with npm and launched from dist/server.js.

Hyperbrowser Cursor configuration

1. Choose Cursor configuration scope

   For Hyperbrowser MCP Server, open Project: .cursor/mcp.json User: ~/.cursor/mcp.json. Merge into mcpServers at project or user scope.

2. Add Hyperbrowser MCP Server to Cursor

   Use the mcp-hyperbrowserai entry below in mcpServers. Keep Hyperbrowser MCP Server's documented stdio connection fields and your other Cursor entries.

3. Check Hyperbrowser MCP Server in Cursor

   Hyperbrowser MCP Server: Enable in Cursor’s MCP settings; inspect tools.

{
  "mcpServers": {
    "mcp-hyperbrowserai": {
      "command": "npx",
      "args": [
        "-y",
        "hyperbrowser-mcp"
      ],
      "env": {
        "HYPERBROWSER_API_KEY": "<Hyperbrowser API key>"
      }
    }
  }
}

Hyperbrowser tools available to Cursor

Hyperbrowser's stored tool list documents 10 tools; compare it with Cursor's connected tool list, because the stored list is not a live check.

scrape_webpage

Find scrape_webpage under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

crawl_webpages

Find crawl_webpages under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

extract_structured_data

Find extract_structured_data under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

browser_use_agent

Find browser_use_agent under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

openai_computer_use_agent

Find openai_computer_use_agent under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

claude_computer_use_agent

Find claude_computer_use_agent under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Delegate complex browser interactions to Claude computer use.

search_with_bing

Find search_with_bing under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Find web results through Bing.

create_profile

Find create_profile under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Create a persistent Hyperbrowser profile.

delete_profile

Find delete_profile under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Remove a persistent Hyperbrowser profile.

list_profiles

Find list_profiles under Hyperbrowser in Cursor's MCP settings; inspect its arguments when the agent requests a call.

List persistent browser profiles with optional pagination.

Hyperbrowser: full stored tool descriptions

Troubleshooting Hyperbrowser in Cursor

• Cursor must find npx hyperbrowser-mcp (Node.js/npm) for Hyperbrowser MCP Server. Enable the project/user entry in MCP settings and inspect its tools.
• Review HYPERBROWSER_API_KEY for Hyperbrowser MCP Server before sharing project .cursor/mcp.json; project scope travels with the repository.
• Hyperbrowser MCP Server uses stdio here: Cursor must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
• Known limitation: Requires a Hyperbrowser API key
• Known limitation: The MCP toolset exposes only a subset of Hyperbrowser API features
• General Cursor troubleshooting lives in the /clients/cursor guide.

Frequently asked questions