Unpack an Office document (.docx, .pptx, .xlsx) to a directory.
AI agents call unpack_office_document to retrieve information from PPTX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Unpacking extracts the contents of an Office document (which is a ZIP archive internally) into a directory. This is a read/extraction operation with no modification of the original file. It creates new files in a directory, which could be considered a Write, but the primary action is reading and extracting existing data. The blast radius is low as it only extracts document contents locally.
From the tool's definition Unpack an Office document (.docx, .pptx, .xlsx) to a directory
Attacks that exploit this kind of access
Unpack an Office document (.docx, .pptx, .xlsx) to a directory. It is categorised as a Read tool in the PPTX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PPTX MCP Server MCP server in PolicyLayer and add a rule for unpack_office_document: 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 PPTX MCP Server. Nothing to install.
unpack_office_document 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 unpack_office_document 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 unpack_office_document. 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.
unpack_office_document is provided by the PPTX MCP Server MCP server (shjanjua/pptx-mcp-server). 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 →