AI agents call search_audits to retrieve information from Oathe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves audit data without side effects. It does not modify, delete, execute operations, or move resources. The search function is inherently read-only, making it the least risky category. Low severity reflects the minimal blast radius if misused—an agent could only retrieve audit information already available in the system.
From the tool's definition Tool name 'search_audits' and description 'Search all completed Oathe behavioral security audits' indicate a query/retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Search all completed Oathe behavioral security audits. It is categorised as a Read tool in the Oathe MCP Server, which means it retrieves data without modifying state.
Register the Oathe MCP server in PolicyLayer and add a rule for search_audits: 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 Oathe. Nothing to install.
search_audits 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 search_audits 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 search_audits. 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.
search_audits is provided by the Oathe MCP server (oathe-ai/oathe-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 →