modify_index · Azure Ai Search Python Preview MCP

WHAT IT DOES

What modify_index does on Azure Ai Search Python Preview

AI agents use modify_index to create or update resources in Azure Ai Search Python Preview — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Azure Ai Search Python Preview environment.

WHY IT NEEDS A POLICY

Why modify_index needs a policy

This tool modifies (but does not delete) an existing search index definition, which is a reversible Write operation. While it affects search infrastructure that could impact availability if misconfigured, it is not Destructive (index not deleted, data not lost) and not Execute (no arbitrary code execution).

From the tool's definition Tool description states it 'Updates an AI Search index with a new index definition.' The verb 'Updates' and the sibling tools (create_index, delete_index, add_document, delete_document) confirm this is a write operation that modifies search infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

modify_index Rate-limited

modify_index stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "modify_index": {
      "limits": [
        {
          "counter": "modify_index_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Azure Ai Search Python Preview, so you can run agents against it safely.

FAQ

Questions about modify_index

What does the modify_index tool do? +

Updates an AI Search index with a new index definition. It is categorised as a Write tool in the Azure Ai Search Python Preview MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on modify_index? +

Register the Azure Ai Search Python Preview MCP server in PolicyLayer and add a rule for modify_index: 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 Azure Ai Search Python Preview. Nothing to install.

What risk level is modify_index? +

modify_index is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit modify_index? +

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

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

modify_index is provided by the Azure Ai Search Python Preview MCP server (projectacetylcholine/mcp-server-azure-ai-search-python-preview). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.