get_ontology_decisions
AI agents call get_ontology_decisions to retrieve information from OOSDK MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
'Get' typically indicates a read operation that queries or retrieves data without modification. However, in an ontology-driven policy system, 'decisions' could refer to business rules or configurations that, if exposed to an untrusted agent, might enable policy inference attacks or exposure of sensitive governance logic.
From the tool's definition Tool name is 'get_ontology_decisions' — the verb 'get' indicates retrieval. Description is empty, limiting certainty.
Attacks that exploit this kind of access
get_ontology_decisions. It is categorised as a Read tool in the OOSDK MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OOSDK MCP Server MCP server in PolicyLayer and add a rule for get_ontology_decisions: 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 OOSDK MCP Server. Nothing to install.
get_ontology_decisions 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_decisions 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_decisions. 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_decisions is provided by the OOSDK MCP Server MCP server (sunnylabtv-crypto/ai_mcp_multi_agent_oosdk-public). 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 →