AI agents call read_docx to retrieve information from MCP Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries the contents of Word documents with no side effects or data modification. It fits the Read category definition of tools that retrieve or query data without side effects. The severity is low as misuse would only expose document contents that should already be accessible to authorized users, with no destructive or financial impact.
From the tool's definition Tool name 'read_docx' and description '读取Word文档内容' (read Word document content) indicate a read-only operation that retrieves document data without modification.
Attacks that exploit this kind of access
读取Word文档内容. It is categorised as a Read tool in the MCP Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Tools MCP server in PolicyLayer and add a rule for read_docx: 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 MCP Tools. Nothing to install.
read_docx 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 read_docx 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 read_docx. 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.
read_docx is provided by the MCP Tools MCP server (starzzzzzzzzzzzzzz/mcp-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →