Spring AI Chrome MCP Server

@qoxogus

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

qoxogus

关于 Spring AI Chrome MCP Server

暂无概览

#spring-ai #chrome #mcp-server

Spring AI Chrome 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": {
    "spring-ai-chrome-mcp-server": {
      "command": "{JAVA_PATH}",
      "args": [
        "-Dspring.ai.mcp.server.stdio=true",
        "-jar",
        "{JAR_PATH}"
      ]
    }
  }
}

Spring AI Chrome MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Spring AI Chrome MCP Server?

Spring AI Chrome MCP Server is an MCP (Model Context Protocol) server that allows AI assistants to interact with a Chrome browser. It manages multiple browser instances by ID and tabs by index, enabling tasks like opening browsers, searching, navigating, clicking, taking screenshots, extracting text, and managing tabs and cookies.

How to use Spring AI Chrome MCP Server?

To use the server, configure the claude_desktop_config.json with the path to Java and the jar file. The server runs in stdio mode with the command java -Dspring.ai.mcp.server.stdio=true -jar <JAR_PATH>. Once connected, an AI assistant can invoke tools using natural language instructions such as "open browser," "search," "navigate to URL," etc.

Key features of Spring AI Chrome MCP Server

Open and manage multiple Chrome browser instances.
Perform Google searches and navigate to URLs.
Click on links with specific text.
Take screenshots of the current page.
Input text into fields and extract page text.
Manage tabs: open, close, switch, and list.
Retrieve and manage cookies.
Close specific browsers or all browsers.

Use cases of Spring AI Chrome MCP Server

Automate web research by having an AI open browsers, search, and summarize content.
Test web applications by programmatically clicking links and filling forms.
Monitor live data like exchange rates by instructing the AI to search and report.
Perform multi-tab browsing tasks such as opening a new tab with a URL, searching, and closing tabs.

常见问题

How are browsers and tabs identified?

Each browser instance is managed by a unique ID. If not set, the default ID is used. Tabs are managed by index within each browser.

Can I run multiple browsers simultaneously?

Yes, you can open multiple browsers with different IDs and control them independently. Use the `*_by_browser_id` tools to target a specific browser.

What runtime is required?

The server requires Java (JDK 21 or compatible) to run the JAR file. The configuration must specify the full path to the Java executable and the JAR file.

What tools are available for browser control?

Tools include: `open_browser`, `google_search`, `navigate_to_url`, `click_link_with_text`, `take_screenshot`, `input_text`, `extract_page_text`, `get_cookies`, `open_new_tab`, `switch_to_tab`, `close_current_tab`, `get_tab_list`, `close_all_tabs_except_current`, `close_browser`, and `close_all_browsers`. Each also has a `by_browser_id` variant.

Are there any security or authentication considerations?

The server runs locally and interacts with the Chrome browser on the same machine. No authentication is described. It uses MCP stdio transport.

其他分类下的更多 MCP 服务器

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

EverArt