AI agents call chat_with_ppt to retrieve information from ChatPPT-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs intelligent querying and conversational retrieval against indexed PPT documents. It reads and returns information from documents without modifying, deleting, or executing anything. The server description confirms it is a 'querying and analysis' engine. Severity is low as misuse only exposes document contents already stored in the system.
From the tool's definition 与一个或所有PPT文档进行对话 (Chat/converse with one or all PPT documents) — this is a RAG query/retrieval operation against indexed PPT content
Documented attack patterns abuse exactly the kind of access chat_with_ppt gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ChatPPT-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for chat_with_ppt:
{
"version": "1",
"default": "deny",
"tools": {
"chat_with_ppt": {}
}
}chat_with_ppt 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.
与一个或所有PPT文档进行对话. It is categorised as a Read tool in the ChatPPT-MCP MCP Server, which means it retrieves data without modifying state.
Register the ChatPPT- MCP server in PolicyLayer and add a rule for chat_with_ppt: 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 ChatPPT-MCP. Nothing to install.
chat_with_ppt 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 chat_with_ppt 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 chat_with_ppt. 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.
chat_with_ppt is provided by the ChatPPT- MCP server (pingcy/app_chatppt). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ChatPPT-MCP, 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.
4 ChatPPT-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.