Skip to content
Back to search

mcp

A MCP server implementation for hyperbrowser

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/hyperbrowserai--mcp/badge.svg)](/listings/hyperbrowserai--mcp)

HTML

<a href="/listings/hyperbrowserai--mcp"><img src="/api/listings/hyperbrowserai--mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Manual Installation

To install the server, run:

npx hyperbrowser-mcp <YOUR-HYPERBROWSER-API-KEY>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 129 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Hyperbrowser MCP Server
  2. [![smithery badge](https://smithery.ai/badge/@hyperbrowserai/mcp)](https://smithery.ai/server/@hyperbrowserai/mcp)
  3. ![Frame 5](https://github.com/user-attachments/assets/3309a367-e94b-418a-a047-1bf1ad549c0a)
  4. This is Hyperbrowser's Model Context Protocol (MCP) Server. It provides various tools to scrape, extract structured data, and crawl webpages. It also provides easy access to general purpose browser agents like OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use.
  5. More information about the Hyperbrowser can be found [here](https://docs.hyperbrowser.ai/). The hyperbrowser API supports a superset of features present in the mcp server.
  6. More information about the Model Context Protocol can be found [here](https://modelcontextprotocol.io/introduction).
  7. ## Table of Contents
  8. - [Installation](#installation)
  9. - [Usage](#usage)
  10. - [Tools](#tools)
  11. - [Configuration](#configuration)
  12. - [License](#license)
  13. ## Installation
  14. ### Manual Installation
  15. To install the server, run:
  16. ```bash
  17. npx hyperbrowser-mcp <YOUR-HYPERBROWSER-API-KEY>
  18. ```
  19. ## Running on Cursor
  20. Add to `~/.cursor/mcp.json` like this:
  21. ```json
  22. {
  23. "mcpServers": {
  24. "hyperbrowser": {
  25. "command": "npx",
  26. "args": ["-y", "hyperbrowser-mcp"],
  27. "env": {
  28. "HYPERBROWSER_API_KEY": "YOUR-API-KEY"
  29. }
  30. }
  31. }
  32. }
  33. ```
  34. ## Running on Windsurf
  35. Add to your `./codeium/windsurf/model_config.json` like this:
  36. ```json
  37. {
  38. "mcpServers": {
  39. "hyperbrowser": {
  40. "command": "npx",
  41. "args": ["-y", "hyperbrowser-mcp"],
  42. "env": {
  43. "HYPERBROWSER_API_KEY": "YOUR-API-KEY"
  44. }
  45. }
  46. }
  47. }
  48. ```
  49. ### Development
  50. For development purposes, you can run the server directly from the source code.
  51. 1. Clone the repository:
  52. ```sh
  53. git clone git@github.com:hyperbrowserai/mcp.git hyperbrowser-mcp
  54. cd hyperbrowser-mcp
  55. ```
  56. 2. Install dependencies:
  57. ```sh
  58. npm install # or yarn install
  59. npm run build
  60. ```
  61. 3. Run the server:
  62. ```sh
  63. node dist/server.js
  64. ```
  65. ## Claude Desktop app
  66. This is an example config for the Hyperbrowser MCP server for the Claude Desktop client.
  67. ```json
  68. {
  69. "mcpServers": {
  70. "hyperbrowser": {
  71. "command": "npx",
  72. "args": ["--yes", "hyperbrowser-mcp"],
  73. "env": {
  74. "HYPERBROWSER_API_KEY": "your-api-key"
  75. }
  76. }
  77. }
  78. }
  79. ```
  80. ## Tools
  81. * `scrape_webpage` - Extract formatted (markdown, screenshot etc) content from any webpage
  82. * `crawl_webpages` - Navigate through multiple linked pages and extract LLM-friendly formatted content
  83. * `extract_structured_data` - Convert messy HTML into structured JSON
  84. * `search_with_bing` - Query the web and get results with Bing search
  85. * `browser_use_agent` - Fast, lightweight browser automation with the Browser Use agent
  86. * `openai_computer_use_agent` - General-purpose automation using OpenAI’s CUA model
  87. * `claude_computer_use_agent` - Complex browser tasks using Claude computer use
  88. * `create_profile` - Creates a new persistent Hyperbrowser profile.
  89. * `delete_profile` - Deletes an existing persistent Hyperbrowser profile.
  90. * `list_profiles` - Lists existing persistent Hyperbrowser profiles.
  91. ### Installing via Smithery
  92. To install Hyperbrowser MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@hyperbrowserai/mcp):
  93. ```bash
  94. npx -y @smithery/cli install @hyperbrowserai/mcp --client claude
  95. ```
  96. ## Resources
  97. The server provides the documentation about hyperbrowser through the `resources` methods. Any client which can do discovery over resources has access to it.
  98. ## License
  99. This project is licensed under the MIT License.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.