Get hierarchical relationships for a term
AI agents call get_hierarchy to retrieve information from Mcp Ubergraph Query without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves hierarchical relationships (parent/child/sibling terms) from the biomedical ontology without creating, modifying, or deleting any data. It has no side effects and poses minimal risk—typical AI misuse would only return unwanted but harmless information. Classified as Read with low severity.
From the tool's definition Tool name 'get_hierarchy' and description 'Get hierarchical relationships for a term' indicate retrieval of existing ontology data with no modification or deletion. This is a read-only query operation against the Ubergraph biomedical ontology SPARQL endpoint.
Attacks that exploit this kind of access
Get hierarchical relationships for a term. It is categorised as a Read tool in the Mcp Ubergraph Query MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ubergraph Query MCP server in PolicyLayer and add a rule for get_hierarchy: 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 Mcp Ubergraph Query. Nothing to install.
get_hierarchy 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_hierarchy 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_hierarchy. 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_hierarchy is provided by the Mcp Ubergraph Query MCP server (twhetzel/mcp-ubergraph-query). 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 →