Retrieve relatives for a given person ID or list of IDs
AI agents call get_relatives to retrieve information from WikiTree 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 genealogical relationship data from WikiTree without modifying, deleting, or executing any operations. It has no capability to alter data, trigger external processes, or commit financial obligations. The operation is read-only and non-destructive, consistent with low-risk data retrieval.
From the tool's definition Tool description states 'Retrieve relatives' which is a query operation that retrieves genealogical data with no side effects.
Attacks that exploit this kind of access
Retrieve relatives for a given person ID or list of IDs. It is categorised as a Read tool in the WikiTree MCP server MCP Server, which means it retrieves data without modifying state.
Register the WikiTree MCP server MCP server in PolicyLayer and add a rule for get_relatives: 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 WikiTree MCP server. Nothing to install.
get_relatives 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_relatives 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_relatives. 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_relatives is provided by the WikiTree MCP server MCP server (pewu/wikitree-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 →