AI agents call describe_table to retrieve information from MCP SQLite Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Describing a table schema is a read-only query operation that returns structural metadata. It has no side effects, does not execute code, and cannot modify or delete data. The blast radius of misuse is minimal—an agent could learn about database structure but cannot act destructively with this tool alone.
From the tool's definition Tool name is 'describe_table' and description states 'Get the schema information for a specific table' — this retrieves metadata about table structure without modifying or executing arbitrary logic.
Documented attack patterns abuse exactly the kind of access describe_table gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP SQLite Server, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_table:
{
"version": "1",
"default": "deny",
"tools": {
"describe_table": {}
}
}describe_table is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the schema information for a specific table. It is categorised as a Read tool in the MCP SQLite Server MCP Server, which means it retrieves data without modifying state.
Register the MCP SQLite Server 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 MCP SQLite Server. 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 MCP SQLite Server MCP server (johnnyoshika/mcp-server-sqlite-npx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP SQLite Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 MCP SQLite Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.