query_database

THE RISK

High Risk

Why query_database needs a policy

This tool executes arbitrary SQL queries against a database. While named 'query', it executes SQL which could include SELECT, INSERT, UPDATE, DELETE, DROP, or any other SQL statement depending on DBMS permissions. The ability to run arbitrary SQL represents a critical risk since a misused or malicious query could read sensitive data, modify records, or destroy data.

From the tool's definition 'Execute a SQL query' - runs arbitrary SQL against a connected DBMS via ODBC

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

POLICY

How to control query_database

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

policy.json

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

query_database 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 Odbc — 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 Odbc tools

Execute query_database_jsonl Execute a SQL query and return results in JSONL format. Execute query_database_md Execute a SQL query and return results in MD format. Execute spasql_query Execute a SPASQL query and return results. Execute virtuoso_support_ai Tool to use the Virtuoso AI support function Execute chat_prompt_complete Tool to use the OPAL backend to complete chat prompt Read describe_table Retrieve and return a dictionary containing the definition of a table, including column na Read filter_table_names Retrieve and return a list containing information about tables whose names contain the sub Read get_schemas Retrieve and return a list of all schema names from the connected database.

All 15 Mcp Odbc 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 Odbc → 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_database

What does the query_database tool do? +

Execute a SQL query and return results in JSON, JSONL or MD format. It is categorised as a Execute tool in the Mcp Odbc 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_database? +

Register the Mcp Odbc MCP server in PolicyLayer and add a rule for query_database: 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 Odbc. Nothing to install.

What risk level is query_database? +

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

Can I rate-limit query_database? +

Yes. Add a rate_limit block to the query_database 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_database completely? +

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

query_database is provided by the Mcp Odbc MCP server (openlinksoftware/mcp-odbc-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Odbc tool call.

Start from Mcp Odbc, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →