get_person_data
AI agents call get_person_data to retrieve information from Rejestr Io MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the naming convention and server context (a business registry providing lookup/search functionality), this tool almost certainly retrieves personal or individual information without modifying it. However, the empty description creates uncertainty about exact scope (e.g., whether it retrieves sensitive PII, connections, or financial data).
From the tool's definition Tool named 'get_person_data' with empty description; server context indicates this is part of a business registry system that provides 'company search, beneficiary checks, and financial document retrieval.' Sibling tools like 'get_beneficiary' and…
Attacks that exploit this kind of access
get_person_data. It is categorised as a Read tool in the Rejestr Io MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Rejestr Io MCP Server MCP server in PolicyLayer and add a rule for get_person_data: 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 Rejestr Io MCP Server. Nothing to install.
get_person_data 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 get_person_data 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 get_person_data. 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.
get_person_data is provided by the Rejestr Io MCP Server MCP server (kolegaliterat/rejestr-io-mcp). 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 →