AI agents call query_history to retrieve information from Omnibase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical query execution records for auditing and debugging purposes. It performs no writes, deletes, executions, or financial operations. Even though it may expose details about past SQL commands (including their content), viewing historical logs is fundamentally a read operation.
From the tool's definition Tool description states 'View recent query execution history' and 'Shows tool name, connection, SQL, duration, row count, and status' — purely retrieval of past execution metadata with no mutation or side effects.
Attacks that exploit this kind of access
View recent query execution history. Shows tool name, connection, SQL, duration, row count, and status. Useful for debugging and understanding what queries have been run. It is categorised as a Read tool in the Omnibase MCP Server, which means it retrieves data without modifying state.
Register the Omnibase MCP server in PolicyLayer and add a rule for query_history: 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 Omnibase. Nothing to install.
query_history 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 query_history 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 query_history. 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.
query_history is provided by the Omnibase MCP server (omnibase-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 →