Perform multiple document operations (create, update, delete) in a single API call
AI agents call bulk to permanently remove resources in Octodet Elasticsearch — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The bulk tool explicitly supports delete operations alongside create and update, and operates on multiple documents simultaneously. Since it can irreversibly delete documents at scale in a single call, the most severe applicable category is Destructive. The blast radius is high because a single misuse could delete or corrupt large numbers of documents across an index.
From the tool's definition Perform multiple document operations (create, update, delete) in a single API call
Attacks that exploit this kind of access
Perform multiple document operations (create, update, delete) in a single API call. It is categorised as a Destructive tool in the Octodet Elasticsearch MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Octodet Elasticsearch MCP server in PolicyLayer and add a rule for bulk: 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.
bulk is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the bulk 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 bulk. 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.
bulk 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 →