广告合作
MCP.so
登录

Steel Puppeteer MCP Server

@MCP-Mirror

代码仓库

基本信息

分类

浏览器自动化

传输方式

stdio

作者

MCP-Mirror

关于 Steel Puppeteer MCP Server

Mirror of

#puppeteer#browser-automation#llm-integration

Steel Puppeteer MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "steel-puppeteer": {
      "command": "node",
      "args": [
        "path/to/steel-puppeteer/dist/index.js"
      ],
      "env": {
        "STEEL_LOCAL": "true"
      }
    }
  }
}

Steel Puppeteer MCP Server 工具

9

Navigate to any URL in the browser

Capture screenshots of the entire page or specific elements

Click elements on the page

Fill out input fields

Select an element with SELECT tag

Hover elements on the page

Execute JavaScript in the browser console

Extract content from the current page

Scroll the page to trigger lazy-loading

概览

What is Steel Puppeteer?

Steel Puppeteer is a Model Context Protocol server that provides browser automation capabilities using Puppeteer and Steel. It enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

How to use Steel Puppeteer?

Install dependencies with npm install, build with npm run build, and start the server with npm start. Configure it for Claude Desktop by adding a steel-puppeteer entry to claude_desktop_config.json with the compiled index.js path and appropriate environment variables (STEEL_LOCAL, STEEL_API_KEY, STEEL_URL).

Key features of Steel Puppeteer

  • Browser automation with Puppeteer
  • Steel integration for session management
  • Console log monitoring and capture
  • Screenshot capture of pages or elements
  • JavaScript execution in the browser
  • Web interaction: navigation, clicking, form filling
  • Content extraction with token limit handling
  • Lazy-loading support through scrolling

Use cases of Steel Puppeteer

  • Have an LLM navigate to a URL and take a screenshot.
  • Automate form filling and clicking on a web page.
  • Extract page content or execute custom JavaScript for data mining.
  • Monitor browser console logs during automated testing.
  • Scroll through lazy-loaded pages to capture all content.

常见问题

1

What environment variables are required?

`STEEL_LOCAL` (optional, default "false"): set to "true" for local Steel instance. `STEEL_API_KEY` required only if `STEEL_LOCAL` is "false". `STEEL_URL` optional for custom Steel deployment.

2

How do I run Steel Puppeteer locally?

Install dependencies (`npm install`), build (`npm run build`), then start (`npm start`). If using a local Steel instance, set `STEEL_LOCAL=true` in a `.env` file.

3

What tools does Steel Puppeteer provide?

It provides nine tools: `puppeteer_navigate`, `puppeteer_screenshot`, `puppeteer_click`, `puppeteer_fill`, `puppeteer_select`, `puppeteer_hover`, `puppeteer_evaluate`, `puppeteer_get_content`, and `puppeteer_scroll`.

4

What resources are exposed?

Two resource types: console logs (`console://logs`) for browser console output, and screenshot images (`screenshot://<name>`) captured during sessions.

评论

浏览器自动化 分类下的更多 MCP 服务器

Full Self Browsing

Lakshman Turlapati

DOM-first AI browser automation for Chrome and MCP clients.

194

BrowserTools MCP

AgentDeskAI

Monitor browser logs directly from Cursor and other MCP compatible IDEs.

7.3K

browser-use-mcp-server

co-browser

Browse the web, directly from Cursor etc.

827

Browse Bridge

Share selected Chrome tabs with AI agents. You enable the tab you want to share and maintain the ability to instantly take control. Browse Bridge is a remote MCP server available at https://mcp.browsebridge.com. What c

Nullprint

nullprintai

Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive browser profiles in Nullprint, the AI antidetect browser. Install with one command.

广告合作