Data as of

Hyperbrowser MCP Server for Windsurf: Setup & Config

Windsurf: Hyperbrowser MCP Server combines web scraping, crawling, structured extraction, and cloud browser agents.

What you can do with Hyperbrowser in Windsurf

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

  • Extract page content as Markdown or screenshots
  • Crawl linked pages for content collection
  • Create and manage persistent browser profiles

Before you start: Hyperbrowser in Windsurf

  • 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 Windsurf configuration

  1. Choose Windsurf configuration scope

    For Hyperbrowser MCP Server, open macOS/Linux: ~/.codeium/windsurf/mcp_config.json Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json. Merge into mcpServers; remote endpoints use serverUrl.

  2. Add Hyperbrowser MCP Server to Windsurf

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

  3. Check Hyperbrowser MCP Server in Windsurf

    Hyperbrowser MCP Server: Refresh MCP in Windsurf settings and inspect Cascade’s tools.

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

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

Hyperbrowser tools available to Windsurf

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

scrape_webpage

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for scrape_webpage.

crawl_webpages

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for crawl_webpages.

extract_structured_data

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for extract_structured_data.

browser_use_agent

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for browser_use_agent.

Run explicit browser tasks with the Browser Use cloud agent.

openai_computer_use_agent

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for openai_computer_use_agent.

Delegate general browser interactions to OpenAI computer use.

claude_computer_use_agent

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for claude_computer_use_agent.

search_with_bing

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for search_with_bing.

create_profile

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for create_profile.

Create a persistent Hyperbrowser profile.

delete_profile

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for delete_profile.

Remove a persistent Hyperbrowser profile.

list_profiles

After refreshing Hyperbrowser in Windsurf settings, check Cascade's tool list for list_profiles.

List persistent browser profiles with optional pagination.

Hyperbrowser: full stored tool descriptions

Troubleshooting Hyperbrowser in Windsurf

  • Check npx hyperbrowser-mcp (Node.js/npm) on the machine running Windsurf's MCP integration for Hyperbrowser MCP Server; refresh MCP and inspect Cascade's tools.
  • Check HYPERBROWSER_API_KEY for Hyperbrowser MCP Server; do not bypass a Windsurf permission error with a broad administrator token.
  • Hyperbrowser MCP Server uses stdio here: Windsurf 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 Windsurf troubleshooting lives in the /clients/windsurf guide.

Hyperbrowser MCP Server — details. Windsurf guide

Frequently asked questions

Windsurf reads Hyperbrowser MCP Server under mcpServers in ~/.codeium/windsurf/mcp_config.json on macOS/Linux; Windows uses %USERPROFILE%\.codeium\windsurf\mcp_config.json.

Windsurf's mcp-hyperbrowserai example uses stdio.

Hyperbrowser MCP Server's Windsurf configuration invokes npx hyperbrowser-mcp (Node.js/npm).

Windsurf's Hyperbrowser MCP Server example references HYPERBROWSER_API_KEY. Check these names if startup or authentication fails; the example alone does not distinguish required from optional values.

Hyperbrowser MCP Server's stored list contains 10 tools, including scrape_webpage, crawl_webpages, extract_structured_data. Compare those names with Windsurf's connected tool list; the stored list is not a live check.

Yes. extract_structured_data uses a schema to shape the extracted webpage data.

No. The README says the API includes additional features beyond the MCP server.