Create a new Elasticsearch index with optional settings and mappings
AI agents use create_index to create or update resources in Octodet Elasticsearch — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Octodet Elasticsearch environment.
This tool creates a new index, which is a reversible write operation. While it modifies the Elasticsearch cluster state, the action can be undone by deleting the index. It does not irreversibly destroy data (not Destructive) nor execute arbitrary commands (not Execute).
From the tool's definition Tool name 'create_index' and description 'Create a new Elasticsearch index with optional settings and mappings' indicate data structure creation without data deletion.
Attacks that exploit this kind of access
Create a new Elasticsearch index with optional settings and mappings. It is categorised as a Write tool in the Octodet Elasticsearch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Octodet Elasticsearch 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 Octodet Elasticsearch. Nothing to install.
create_index is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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.
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.
create_index 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →