Get basic information about the Earth616 ontology
AI agents call get_ontology_info to retrieve information from Earth616 Vocabulary Service without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries information about an ontology—a read-only operation with no side effects, no data modification, no code execution, and no destructive or financial impact. It aligns with the Read category pattern of information retrieval tools like 'get', 'fetch', or 'list'.
From the tool's definition Tool name 'get_ontology_info' and description 'Get basic information about the Earth616 ontology' indicate a retrieval operation that queries metadata about an ontology without modifying data.
Attacks that exploit this kind of access
Get basic information about the Earth616 ontology. It is categorised as a Read tool in the Earth616 Vocabulary Service MCP Server, which means it retrieves data without modifying state.
Register the Earth616 Vocabulary Service MCP server in PolicyLayer and add a rule for get_ontology_info: 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 Earth616 Vocabulary Service. Nothing to install.
get_ontology_info 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_ontology_info 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_ontology_info. 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_ontology_info is provided by the Earth616 Vocabulary Service MCP server (la3d/mcp_vocabulary_service). 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 →