describe_table
AI agents call describe_table to retrieve information from Sql Explorer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server's read-only architecture, safety mechanisms, and the descriptive nature of the tool name strongly indicate this retrieves table metadata without modification. No evidence of side effects or data mutation. Confidence slightly reduced from 1.0 due to empty tool description, but server context makes classification clear.
From the tool's definition Tool is part of sql-explorer-mcp server explicitly described as 'Read-only MCP server' with 'three-layer safety using AST validation and linting'. Tool name 'describe_table' aligns with read-only operations (analogous to DESCRIBE or SHOW COLUMNS in SQL).
Attacks that exploit this kind of access
describe_table. It is categorised as a Read tool in the Sql Explorer MCP Server, which means it retrieves data without modifying state.
Register the Sql Explorer MCP server in PolicyLayer and add a rule for describe_table: 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 Sql Explorer. Nothing to install.
describe_table 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 describe_table 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 describe_table. 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.
describe_table is provided by the Sql Explorer MCP server (pawansingh3889/sql-explorer-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 →