Data as of
Hyperbrowser MCP Server for VS Code: Setup & Config
VS Code: Hyperbrowser MCP Server combines web scraping, crawling, structured extraction, and cloud browser agents.
What you can do with Hyperbrowser in VS Code
Pick it when an assistant needs both web extraction and a choice of cloud browser agents.
- Crawl linked pages for content collection
- Convert webpage content into schema-shaped data
- Delegate interactive tasks to cloud browser agents
Before you start: Hyperbrowser in VS 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 VS Code configuration
Choose VS Code configuration scope
For Hyperbrowser MCP Server, open Workspace: .vscode/mcp.json. Merge into servers; preserve existing inputs.
Add Hyperbrowser MCP Server to VS Code
Use the mcp-hyperbrowserai entry below in servers. Keep Hyperbrowser MCP Server's documented stdio connection fields and your other VS Code entries.
Check Hyperbrowser MCP Server in VS Code
Hyperbrowser MCP Server: Start in VS Code’s MCP controls; inspect output and trust prompts.
Config file · Workspace: .vscode/mcp.json
{
"servers": {
"mcp-hyperbrowserai": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"hyperbrowser-mcp"
],
"env": {
"HYPERBROWSER_API_KEY": "<Hyperbrowser API key>"
}
}
}
}Hyperbrowser tools available to VS Code
Hyperbrowser's stored tool list documents 10 tools; compare it with VS Code's connected tool list, because the stored list is not a live check.
- scrape_webpage
Look for scrape_webpage among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
Retrieve one page as text, HTML, links, or screenshots with browser options.
- crawl_webpages
Look for crawl_webpages among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
Collect content from linked pages starting at a selected URL.
- extract_structured_data
Look for extract_structured_data among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
Extract webpage information according to a supplied schema.
- browser_use_agent
Look for browser_use_agent among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
- openai_computer_use_agent
Look for openai_computer_use_agent among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
- claude_computer_use_agent
Look for claude_computer_use_agent among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
Delegate complex browser interactions to Claude computer use.
- search_with_bing
Look for search_with_bing among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
Find web results through Bing.
- create_profile
Look for create_profile among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
- delete_profile
Look for delete_profile among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
- list_profiles
Look for list_profiles among VS Code's agent-mode tools after starting Hyperbrowser through the MCP controls.
Troubleshooting Hyperbrowser in VS Code
- Make npx hyperbrowser-mcp (Node.js/npm) available in the workspace, container, or remote environment hosting Hyperbrowser MCP Server. Start through VS Code's MCP controls; inspect output and trust prompts.
- For Hyperbrowser MCP Server, keep HYPERBROWSER_API_KEY out of version control; VS Code documents input variables and secret handling.
- Hyperbrowser MCP Server uses stdio here: VS 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 VS Code troubleshooting lives in the /clients/vscode guide.
Hyperbrowser MCP Server — details. VS Code guide