AI agents call extract_document_media to retrieve information from Document Reader MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and extracts media elements (images and links) from documents—a read-only operation with no side effects. The server context confirms it processes documents to extract data rather than modify them. No code execution, data modification, deletion, or financial operations are involved.
From the tool's definition Tool name 'extract_document_media' and description '提取文档中的图片和链接信息' (extract images and links from documents) indicates retrieval of embedded media and link data from documents without modification or deletion of the source material.
Documented attack patterns abuse exactly the kind of access extract_document_media gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Document Reader MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for extract_document_media:
{
"version": "1",
"default": "deny",
"tools": {
"extract_document_media": {}
}
}extract_document_media is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
提取文档中的图片和链接信息. It is categorised as a Read tool in the Document Reader MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Document Reader MCP Server MCP server in PolicyLayer and add a rule for extract_document_media: 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 Document Reader MCP Server. Nothing to install.
extract_document_media is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the extract_document_media 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.
Set action: deny in the PolicyLayer policy for extract_document_media. 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.
extract_document_media is provided by the Document Reader MCP Server MCP server (qitianfeng/document-reader-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Document Reader MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Document Reader MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.