run_query

THE RISK

High Risk

Why run_query needs a policy

This tool executes database queries whose effects depend entirely on the query content provided by the caller. Even if safety controls exist server-wide, the tool's core function is to run arbitrary code (SQL) against a database.

From the tool's definition Tool name 'run_query' combined with description 'Run a query in a ClickHouse database' indicates execution of arbitrary database queries.

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

POLICY

How to control run_query

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

policy.json

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

run_query 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 ClickHouse — 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 ClickHouse tools

Destructive cloud_delete_api_key Delete an API key. Destructive cloud_delete_clickpipe Delete a ClickPipe. Destructive cloud_delete_invitation Delete/cancel an invitation. Destructive cloud_delete_query_endpoint_config Delete query endpoint configuration for a service (experimental). Destructive cloud_delete_reverse_private_endpoint Delete a reverse private endpoint (beta). Destructive cloud_delete_service Delete a service (must be stopped first). Destructive cloud_remove_member Remove a member from the organization. Execute cloud_update_clickpipe_state Start, stop, or resync a ClickPipe.

All 55 MCP ClickHouse 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 ClickHouse → 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 run_query

What does the run_query tool do? +

Run a query in a ClickHouse database. It is categorised as a Execute tool in the MCP ClickHouse MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_query? +

Register the MCP ClickHouse MCP server in PolicyLayer and add a rule for run_query: 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 ClickHouse. Nothing to install.

What risk level is run_query? +

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

Can I rate-limit run_query? +

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

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

run_query is provided by the MCP ClickHouse MCP server (oualib/chmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP ClickHouse tool call.

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

CHECK YOUR STACK →