Update entities in knowledge graph (memory)
AI agents use update_entities to create or update resources in Elasticsearch Knowledge Graph for MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Elasticsearch Knowledge Graph for MCP environment.
This tool modifies existing entities within the knowledge graph but does not delete or irreversibly destroy data (that would be delete_entities). Updates are reversible through subsequent edits, making this a Write operation.
From the tool's definition Tool name 'update_entities' and description 'Update entities in knowledge graph (memory)' indicate modification of stored data. The verb 'update' and context of a knowledge graph storing entities confirm reversible data changes.
Documented attack patterns abuse exactly the kind of access update_entities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Elasticsearch Knowledge Graph for MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for update_entities:
{
"version": "1",
"default": "deny",
"tools": {
"update_entities": {
"limits": [
{
"counter": "update_entities_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} update_entities 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.
Free to start. No card required.
Update entities in knowledge graph (memory). It is categorised as a Write tool in the Elasticsearch Knowledge Graph for MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Elasticsearch Knowledge Graph for MCP server in PolicyLayer and add a rule for update_entities: 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 Elasticsearch Knowledge Graph for MCP. Nothing to install.
update_entities 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 update_entities 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 update_entities. 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.
update_entities is provided by the Elasticsearch Knowledge Graph for MCP server (j3k0/mcp-brain-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Elasticsearch Knowledge Graph for 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.
23 Elasticsearch Knowledge Graph for MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.