query_clickhouse_resource · PyTorch HUD MCP Server MCP

WHAT IT DOES

What query_clickhouse_resource does on PyTorch HUD MCP Server

AI agents invoke query_clickhouse_resource to trigger actions in PyTorch HUD MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why query_clickhouse_resource needs a policy

This tool executes named queries against a ClickHouse database with parameters. While it appears to be used for analytics reads, the description says 'Run a query' which implies arbitrary execution. ClickHouse queries could include mutations, deletions, or DDL depending on what named queries are available.

From the tool's definition "Run a ClickHouse query by name with parameters"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_clickhouse_resource Rate-limited

query_clickhouse_resource 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches PyTorch HUD MCP Server, so you can run agents against it safely.

FAQ

Questions about query_clickhouse_resource

What does the query_clickhouse_resource tool do? +

Run a ClickHouse query by name with parameters. It is categorised as a Execute tool in the PyTorch HUD MCP 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_clickhouse_resource? +

Register the PyTorch HUD MCP Server MCP server in PolicyLayer and add a rule for query_clickhouse_resource: 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 PyTorch HUD MCP Server. Nothing to install.

What risk level is query_clickhouse_resource? +

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

Can I rate-limit query_clickhouse_resource? +

Yes. Add a rate_limit block to the query_clickhouse_resource 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_clickhouse_resource completely? +

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

query_clickhouse_resource is provided by the PyTorch HUD MCP Server MCP server (izaitsevfb/claude-pytorch-treehugger). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.