Data as of

Hyperbrowser MCP Server for Claude Code: Setup & Config

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

What you can do with Hyperbrowser in Claude Code

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

  • Convert webpage content into schema-shaped data
  • Delegate interactive tasks to cloud browser agents
  • Create and manage persistent browser profiles

Before you start: Hyperbrowser in Claude Code

  • 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 Claude Code configuration

  1. Choose Claude Code configuration scope

    For Hyperbrowser MCP Server, open Project scope: .mcp.json at the repository root. Project JSON: merge into mcpServers; user scope: use the CLI.

  2. Add Hyperbrowser MCP Server to Claude Code

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

  3. Check Hyperbrowser MCP Server in Claude Code

    Hyperbrowser MCP Server: Inspect claude mcp list and /mcp status.

Config file · Project scope: .mcp.json at the repository root

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

CLI (POSIX shell)
claude mcp add-json --scope project 'mcp-hyperbrowserai' '{"type":"stdio","command":"npx","args":["-y","hyperbrowser-mcp"],"env":{"HYPERBROWSER_API_KEY":"<Hyperbrowser API key>"}}'

Hyperbrowser tools available to Claude Code

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

scrape_webpage

For Hyperbrowser's scrape_webpage, review the permission request and arguments in Claude Code before approval.

Retrieve one page as text, HTML, links, or screenshots with browser options.

crawl_webpages

For Hyperbrowser's crawl_webpages, review the permission request and arguments in Claude Code before approval.

Collect content from linked pages starting at a selected URL.

extract_structured_data

For Hyperbrowser's extract_structured_data, review the permission request and arguments in Claude Code before approval.

Extract webpage information according to a supplied schema.

browser_use_agent

For Hyperbrowser's browser_use_agent, review the permission request and arguments in Claude Code before approval.

openai_computer_use_agent

For Hyperbrowser's openai_computer_use_agent, review the permission request and arguments in Claude Code before approval.

claude_computer_use_agent

For Hyperbrowser's claude_computer_use_agent, review the permission request and arguments in Claude Code before approval.

search_with_bing

For Hyperbrowser's search_with_bing, review the permission request and arguments in Claude Code before approval.

create_profile

For Hyperbrowser's create_profile, review the permission request and arguments in Claude Code before approval.

Create a persistent Hyperbrowser profile.

delete_profile

For Hyperbrowser's delete_profile, review the permission request and arguments in Claude Code before approval.

Remove a persistent Hyperbrowser profile.

list_profiles

For Hyperbrowser's list_profiles, review the permission request and arguments in Claude Code before approval.

Hyperbrowser: full stored tool descriptions

Troubleshooting Hyperbrowser in Claude Code

  • If Hyperbrowser MCP Server fails to start, check npx hyperbrowser-mcp (Node.js/npm), the working directory, and Claude Code's selected scope; inspect claude mcp list and /mcp.
  • Hyperbrowser MCP Server: check HYPERBROWSER_API_KEY; keep credentials out of shared .mcp.json.
  • Hyperbrowser MCP Server uses stdio here: Claude Code 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 Claude Code troubleshooting lives in the /clients/claude-code guide.

Hyperbrowser MCP Server — details. Claude Code guide

Frequently asked questions

Register Hyperbrowser MCP Server with the displayed claude mcp add-json --scope project command, or merge the JSON into .mcp.json at the repository root.

Claude Code's mcp-hyperbrowserai example uses stdio.

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

Claude Code'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 Claude Code's connected tool list; the stored list is not a live check.

Browser Use, OpenAI computer use, and Claude computer use are exposed.

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