AI agents call mcp_table_analysis 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.
This tool retrieves and queries database schema metadata (table structure, columns, keys, indexes, constraints) without creating, modifying, deleting, or executing any data-altering operations. The description contains only informational keywords (analysis, including, structure) with no side-effect verbs. It is purely a Read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name and description indicate analysis operations: 'table analysis including structure, columns, keys, indexes, and constraints' — all read-only metadata queries with no modification capability.
Attacks that exploit this kind of access
Comprehensive SQL Server table analysis including structure, columns, keys, indexes, and constraints. 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_table_analysis: 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_table_analysis 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_table_analysis 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_table_analysis. 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_table_analysis 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 →