// SCAN REPORT

MCP Browser Text Reader

7 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 4 Jul 2026

3 can modify or destroy data

4 read-only

7 tools total

Community server · catalogue entry verified 04/07/2026

How to control MCP Browser Text Reader ↓

TOOL MAP

What MCP Browser Text Reader exposes to your agents

Read (4) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP Browser Text Reader tools

Execute · High launch_chrome_manually Launching a browser is an Execute category action because it triggers an external operation (Chrome process) whose side effects depend on what the browser subsequently does. Execute · High navigate_to_page Navigation is an Execute action because it triggers external browser operations whose effects depend on the URL argument. Write · Medium close_browser 关闭浏览器实例

3 of MCP Browser Text Reader's 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Browser Text Reader

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Browser Text Reader, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "close_browser": {
    "limits": [
      {
        "counter": "close_browser_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_browser_status": {
    "limits": [
      {
        "counter": "get_browser_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP Browser Text Reader — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP BROWSER TEXT READER →

Instant setup, no code required.

FULL CATALOGUE

All 7 MCP Browser Text Reader tools

EXECUTE 2 tools

Execute launch_chrome_manually 手动启动Chrome浏览器（可见窗口） Execute navigate_to_page 导航到指定URL

WRITE 1 tools

Write close_browser 关闭浏览器实例

READ 4 tools

Read get_browser_status 获取浏览器连接状态 Read get_current_page_text 获取当前浏览器页面的文本内容 Read get_page_info 获取当前页面的基本信息（标题、URL等） Read get_page_text 获取指定URL页面的文本内容

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP Browser Text Reader

How do I prevent bulk modifications through MCP Browser Text Reader? +

The MCP Browser Text Reader server has 1 write tools including close_browser. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP Browser Text Reader.

How many tools does the MCP Browser Text Reader MCP server expose? +

7 tools across 3 categories: Execute, Read, Write. 4 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on MCP Browser Text Reader? +

Register the MCP Browser Text Reader MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP Browser Text Reader tool call.

Deterministic rules across all 7 MCP Browser Text Reader tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP BROWSER TEXT READER →

Instant setup, no code required.

7 MCP Browser Text Reader tools catalogued and risk-classified — across an index of 43,000+ MCP servers.