Low Risk

describe-table

Get detailed column info, primary keys, and foreign keys for a table.

How to control describe-table ↓

What describe-table does on Tusk

AI agents call describe-table to retrieve information from Tusk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why describe-table needs a policy

The describe-table tool performs schema introspection to return structural information about a table without querying, modifying, or deleting any actual data. This is a classic Read operation with minimal risk; the worst-case misuse scenario would be information disclosure about table structure, which has limited impact in most contexts.

From the tool's definition Tool description explicitly states it retrieves 'detailed column info, primary keys, and foreign keys' — purely informational metadata queries. Server is described as 'read-only' and 'SELECT-only' with no modification or execution capabilities.

Documented attack patterns abuse exactly the kind of access describe-table gives an agent:

How to control describe-table

PolicyLayer is an MCP gateway — it sits between your AI agents and Tusk, and nothing reaches the server without passing your rules. This is the rule we recommend for describe-table:

policy.json
{
  "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.

  1. Create a free account and register Tusk — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about describe-table

What does the describe-table tool do? +

Get detailed column info, primary keys, and foreign keys for a table. It is categorised as a Read tool in the Tusk MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on describe-table? +

Register the Tusk 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 Tusk. Nothing to install.

What risk level is describe-table? +

describe-table is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit describe-table? +

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.

How do I block describe-table completely? +

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.

What MCP server provides describe-table? +

describe-table is provided by the Tusk MCP server (volveezz/tusk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tusk tool call.

Start from Tusk, 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.

4 Tusk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.