Menjawab pertanyaan tentang UU PDP.
AI agents call tanya_pdp to retrieve information from PDP 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 queries legal information from Indonesia's PDP law using RAG (Retrieval-Augmented Generation). It has no capability to modify, delete, execute external commands, or move money. The worst-case misuse—returning incorrect legal information—is informational only and does not cause irreversible data loss or unauthorized actions. Classification as Read with low severity is appropriate.
From the tool's definition Tool name 'tanya_pdp' (ask PDP) and description 'Menjawab pertanyaan tentang UU PDP' (Answer questions about PDP Law) indicate a Q&A/question-answering function.
Attacks that exploit this kind of access
Menjawab pertanyaan tentang UU PDP. It is categorised as a Read tool in the PDP MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PDP MCP Server MCP server in PolicyLayer and add a rule for tanya_pdp: 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 PDP MCP Server. Nothing to install.
tanya_pdp 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 tanya_pdp 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 tanya_pdp. 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.
tanya_pdp is provided by the PDP MCP Server MCP server (vibecoding4-jc/pdp-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 →