query_data

THE RISK

High Risk

Why query_data needs a policy

This tool runs arbitrary SQL queries against a database. While it may be intended for read-only SELECT queries, the description says 'execute a SQL query' without restricting to read-only operations. An AI agent could potentially run destructive SQL (DROP, DELETE, UPDATE) depending on database permissions. The blast radius is high given it operates on enterprise data warehouses (Databricks) and local databases.

From the tool's definition Execute a SQL query on the database and return results

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

POLICY

How to control query_data

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Data Visualization Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query_data:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_data": {
      "limits": [
        {
          "counter": "query_data_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

query_data stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register MCP Data Visualization Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Data Visualization Server tools

Write change_database Connect to a different DuckDB database file Write load_csv_data Load CSV file into the database as a new table Write configure_chart Configure chart parameters by answering column selection questions Write create_interactive_dashboard Generate an interactive HTML dashboard with filtering controls and multiple visualizations Write create_sample_chart Create a sample chart for testing (useful for development) Write create_visualization Start creating a data visualization from natural language request Write select_database_by_number Select a database by its number from the browse results Write select_downloads_database_by_number Select a database by its number from the Downloads browse results

All 28 MCP Data Visualization Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Data Visualization Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about query_data

What does the query_data tool do? +

Execute a SQL query on the database and return results. It is categorised as a Execute tool in the MCP Data Visualization Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_data? +

Register the MCP Data Visualization Server MCP server in PolicyLayer and add a rule for query_data: 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 Data Visualization Server. Nothing to install.

What risk level is query_data? +

query_data is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_data? +

Yes. Add a rate_limit block to the query_data 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 query_data completely? +

Set action: deny in the PolicyLayer policy for query_data. 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 query_data? +

query_data is provided by the MCP Data Visualization Server MCP server (xoniks/mcp-visualization-duckdb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Data Visualization Server tool call.

Start from MCP Data Visualization Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →