SearchIndexTool · Opensearch MCP: Risk & Policy

WHAT IT DOES

What SearchIndexTool does on Opensearch

AI agents invoke SearchIndexTool to trigger actions in Opensearch. 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 SearchIndexTool needs a policy

While searching is generally a read operation, executing arbitrary DSL queries against OpenSearch can include script-based queries (Painless scripts), expensive aggregations that strain the cluster, and potentially access sensitive data across indices.

From the tool's definition 'Searches an index using a query written in query domain-specific language (DSL)' — arbitrary DSL queries can include complex aggregations, script queries, or potentially expensive operations beyond simple reads

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

SearchIndexTool Rate-limited

SearchIndexTool 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": {
    "SearchIndexTool": {
      "limits": [
        {
          "counter": "searchindextool_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 Opensearch, so you can run agents against it safely.

FAQ

Questions about SearchIndexTool

What does the SearchIndexTool tool do? +

Searches an index using a query written in query domain-specific language (DSL) in OpenSearch. It is categorised as a Execute tool in the Opensearch MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on SearchIndexTool? +

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

What risk level is SearchIndexTool? +

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

Can I rate-limit SearchIndexTool? +

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

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

SearchIndexTool is provided by the Opensearch MCP server (rithinpullela/opensearch-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.