AI agents call search_objects to retrieve information from A2db without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches or queries database objects, which is a retrieval operation with no side effects. It returns results without creating, modifying, or deleting data. The low severity reflects minimal blast radius if misused—an agent could only retrieve information it may be unauthorized to see, not alter system state.
From the tool's definition Tool name 'search_objects' and description 'Search database objects' indicate data retrieval without modification. Sibling tools include 'execute' (which would handle modifications) and 'list_connections', confirming this tool's read-only purpose.
Attacks that exploit this kind of access
Search database objects. It is categorised as a Read tool in the A2db MCP Server, which means it retrieves data without modifying state.
Register the A2db MCP server in PolicyLayer and add a rule for search_objects: 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 A2db. Nothing to install.
search_objects 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_objects 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_objects. 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_objects is provided by the A2db MCP server (yoselabs/a2db). 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 →