Low Risk

dlp_preview_table

Returns sample rows from a database table or collection. Default 5 rows, max 20.

How to control dlp_preview_table ↓

What dlp_preview_table does on Database Lookup Protocol (DLP)

AI agents call dlp_preview_table to retrieve information from Database Lookup Protocol (DLP) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why dlp_preview_table needs a policy

This tool only retrieves and displays sample data from a database table with a built-in safety limit. It has no capability to modify, delete, or execute arbitrary code. The blast radius of misuse is minimal—an AI agent could only access limited preview data that is already intended to be readable. This is a classic Read operation with no side effects.

From the tool's definition Tool description states 'Returns sample rows from a database table or collection' with a limit of max 20 rows. Server description emphasizes 'read-only access' and the tool name contains 'preview' which indicates data inspection without modification.

Documented attack patterns abuse exactly the kind of access dlp_preview_table gives an agent:

How to control dlp_preview_table

PolicyLayer is an MCP gateway — it sits between your AI agents and Database Lookup Protocol (DLP), and nothing reaches the server without passing your rules. This is the rule we recommend for dlp_preview_table:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "dlp_preview_table": {}
  }
}

dlp_preview_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 Database Lookup Protocol (DLP) — 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 dlp_preview_table

What does the dlp_preview_table tool do? +

Returns sample rows from a database table or collection. Default 5 rows, max 20. It is categorised as a Read tool in the Database Lookup Protocol (DLP) MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on dlp_preview_table? +

Register the Database Lookup Protocol (DLP) MCP server in PolicyLayer and add a rule for dlp_preview_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 Database Lookup Protocol (DLP). Nothing to install.

What risk level is dlp_preview_table? +

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

Can I rate-limit dlp_preview_table? +

Yes. Add a rate_limit block to the dlp_preview_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 dlp_preview_table completely? +

Set action: deny in the PolicyLayer policy for dlp_preview_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 dlp_preview_table? +

dlp_preview_table is provided by the Database Lookup Protocol (DLP) MCP server (kalyangupta12/database-lookup-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Database Lookup Protocol (DLP) tool call.

Start from Database Lookup Protocol (DLP), 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.

3 Database Lookup Protocol (DLP) 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.