execute_custom_query · OpenReplay MCP Server MCP

WHAT IT DOES

What execute_custom_query does on OpenReplay MCP Server

AI agents invoke execute_custom_query to trigger actions in OpenReplay 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 execute_custom_query needs a policy

This tool permits execution of arbitrary queries against a ClickHouse database based on user input. While the context (OpenReplay analytics) suggests read-heavy use cases, the ability to execute 'custom' SQL-like queries means an AI agent could potentially craft queries with side effects (UPDATE, DELETE, DROP) depending on database permissions, or extract sensitive user session data at scale.

From the tool's definition Tool name 'execute_custom_query' combined with description stating it 'Execute[s] a custom query on the session data (supports SQL-like syntax for ClickHouse)' indicates arbitrary code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_custom_query Rate-limited

execute_custom_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_custom_query": {
      "limits": [
        {
          "counter": "execute_custom_query_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 OpenReplay MCP Server, so you can run agents against it safely.

FAQ

Questions about execute_custom_query

What does the execute_custom_query tool do? +

Execute a custom query on the session data (supports SQL-like syntax for ClickHouse). It is categorised as a Execute tool in the OpenReplay 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 execute_custom_query? +

Register the OpenReplay MCP Server MCP server in PolicyLayer and add a rule for execute_custom_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 OpenReplay MCP Server. Nothing to install.

What risk level is execute_custom_query? +

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

Can I rate-limit execute_custom_query? +

Yes. Add a rate_limit block to the execute_custom_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 execute_custom_query completely? +

Set action: deny in the PolicyLayer policy for execute_custom_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 execute_custom_query? +

execute_custom_query is provided by the OpenReplay MCP Server MCP server (lekt9/openreplay-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.