Low Risk

get_elements_info_by_keyword

根据关键词获取当前标签页中包含该关键词的文本节点的所有元素列表 定位元素时优先使用 Args: keyword (str): 要搜索的关键词 Returns: list: 返回包含关键词的元素列表

How to control get_elements_info_by_keyword ↓

AI agents call get_elements_info_by_keyword to retrieve information from DrissionPageMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool queries the DOM to find and return elements matching a keyword filter. It has no side effects: it does not modify page state, execute scripts, delete data, or trigger external actions. It is a passive read-only search operation, similar to 'get_all_clickable_elements' on the same server. Confidence is high because the description and return type clearly indicate data retrieval only.

From the tool's definition Tool description states it 'retrieves...all elements list' (获取...元素列表) containing a keyword from the current page. Returns a list of elements matching search criteria. No modification, deletion, or code execution occurs—purely information retrieval.

Documented attack patterns abuse exactly the kind of access get_elements_info_by_keyword gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and DrissionPageMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_elements_info_by_keyword:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_elements_info_by_keyword": {}
  }
}

get_elements_info_by_keyword is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register DrissionPageMCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the get_elements_info_by_keyword tool do? +

根据关键词获取当前标签页中包含该关键词的文本节点的所有元素列表 定位元素时优先使用 Args: keyword (str): 要搜索的关键词 Returns: list: 返回包含关键词的元素列表. It is categorised as a Read tool in the DrissionPageMCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_elements_info_by_keyword? +

Register the DrissionPage MCP server in PolicyLayer and add a rule for get_elements_info_by_keyword: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches DrissionPageMCP. Nothing to install.

What risk level is get_elements_info_by_keyword? +

get_elements_info_by_keyword is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_elements_info_by_keyword? +

Yes. Add a rate_limit block to the get_elements_info_by_keyword rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block get_elements_info_by_keyword completely? +

Set action: deny in the PolicyLayer policy for get_elements_info_by_keyword. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides get_elements_info_by_keyword? +

get_elements_info_by_keyword is provided by the DrissionPage MCP server (wxhzhwxhzh/drissionpagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every DrissionPageMCP tool call.

Deterministic rules across all 37 DrissionPageMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

37 DrissionPageMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.