Medium Risk

create_index

Create a new Elasticsearch index with optional mapping and settings configuration

How to control create_index ↓

What create_index does on Agent Knowledge MCP

AI agents use create_index to create or update resources in Agent Knowledge MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Knowledge MCP environment.

Medium Risk

Why create_index needs a policy

Creating an index is a reversible write operation - the index can be deleted or recreated if needed. It does not delete data, execute arbitrary code, or move money. However, it has medium severity because creating indices with improper configuration could consume significant cluster resources, impact performance, or cause issues for dependent systems.

From the tool's definition Tool name 'create_index' and description 'Create a new Elasticsearch index' explicitly indicate creation of a new data structure. This is a write operation that modifies the Elasticsearch cluster state by adding a new index.

Documented attack patterns abuse exactly the kind of access create_index gives an agent:

How to control create_index

PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Knowledge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_index:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_index": {
      "limits": [
        {
          "counter": "create_index_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_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.

  1. Create a free account and register Agent Knowledge MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_index

What does the create_index tool do? +

Create a new Elasticsearch index with optional mapping and settings configuration. It is categorised as a Write tool in the Agent Knowledge MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_index? +

Register the Agent Knowledge MCP server in PolicyLayer and add a rule for create_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 Agent Knowledge MCP. Nothing to install.

What risk level is create_index? +

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

Can I rate-limit create_index? +

Yes. Add a rate_limit block to the create_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 create_index completely? +

Set action: deny in the PolicyLayer policy for create_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 create_index? +

create_index is provided by the Agent Knowledge MCP server (itshare4u/agentknowledgemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Agent Knowledge MCP tool call.

Start from Agent Knowledge MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

27 Agent Knowledge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.