AI agents call pptx_read_slide to retrieve information from Pptx 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 existing slide content without creating, modifying, deleting, or executing any operations. It has no side effects on the presentation data. The blast radius of misuse is minimal—an AI agent could at most extract information from slides, which does not constitute a security risk comparable to write, execute, or destructive actions.
From the tool's definition Tool name is 'pptx_read_slide' and description states 'Read detailed content of a slide -- all shapes, text, tables.' The verb 'read' and explicit statement of retrieval functionality with no modification capability clearly indicate a query operation.
Attacks that exploit this kind of access
Read detailed content of a slide -- all shapes, text, tables. It is categorised as a Read tool in the Pptx MCP Server, which means it retrieves data without modifying state.
Register the Pptx MCP server in PolicyLayer and add a rule for pptx_read_slide: 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. Nothing to install.
pptx_read_slide 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 pptx_read_slide 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 pptx_read_slide. 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.
pptx_read_slide is provided by the Pptx MCP server (knorq-ai/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 →