update_by_query · Octodet Elasticsearch MCP: Risk & Policy

WHAT IT DOES

What update_by_query does on Octodet Elasticsearch

AI agents invoke update_by_query to trigger actions in Octodet Elasticsearch. 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 update_by_query needs a policy

update_by_query executes a query and applies updates to all matching documents in bulk. This is an Execute-level operation because it triggers an Elasticsearch operation whose scope and side effects depend entirely on the query argument. It could modify a large, unbounded number of documents at once, giving it a high blast radius.

From the tool's definition "Update documents in an Elasticsearch index based on a query" — runs a query-driven bulk update across potentially many documents

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_by_query Rate-limited

update_by_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": {
    "update_by_query": {
      "limits": [
        {
          "counter": "update_by_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 Octodet Elasticsearch, so you can run agents against it safely.

FAQ

Questions about update_by_query

What does the update_by_query tool do? +

Update documents in an Elasticsearch index based on a query. It is categorised as a Execute tool in the Octodet Elasticsearch MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on update_by_query? +

Register the Octodet Elasticsearch MCP server in PolicyLayer and add a rule for update_by_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 Octodet Elasticsearch. Nothing to install.

What risk level is update_by_query? +

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

Can I rate-limit update_by_query? +

Yes. Add a rate_limit block to the update_by_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 update_by_query completely? +

Set action: deny in the PolicyLayer policy for update_by_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 update_by_query? +

update_by_query is provided by the Octodet Elasticsearch MCP server (octodet/elasticsearch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.