AI agents call mcp_search_comprehensive to retrieve information from Mcpql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs database object search and retrieval operations without side effects. While it searches across definitions which could theoretically expose sensitive schema information (hence medium rather than low severity), it remains fundamentally a Read operation.
From the tool's definition Tool description states 'Search across database objects by name and definition' which is a read-only operation. No modifying, executing, or deleting operations are indicated.
Attacks that exploit this kind of access
Search across database objects by name and definition with configurable criteria. It is categorised as a Read tool in the Mcpql MCP Server, which means it retrieves data without modifying state.
Register the Mcpql MCP server in PolicyLayer and add a rule for mcp_search_comprehensive: 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 Mcpql. Nothing to install.
mcp_search_comprehensive 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 mcp_search_comprehensive 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 mcp_search_comprehensive. 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.
mcp_search_comprehensive is provided by the Mcpql MCP server (mcpql). 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 →