CREATE new entities with OBSERVATIONS and optional tags. MANDATORY: If creating multiple entities, use a SINGLE call (batch). Each entity requires a unique name, type, and at least one observation. Ignores existing names. Use search_knowledge first.
AI agents use create_entities to create or update resources in KnowledgeGraph MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KnowledgeGraph MCP Server environment.
This tool creates new records (entities) in the knowledge graph with associated metadata (observations, tags). Creation is reversible via delete_entities, making it Write rather than Destructive. The blast radius is medium because an agent could pollute the knowledge graph with incorrect or malicious entities, but the impact is contained to the knowledge graph itself and remediable through deletion.
From the tool's definition Tool description explicitly states 'CREATE new entities' and 'use a SINGLE call (batch)'. The verb 'CREATE' and the instruction to add observations and tags indicate this creates and modifies data in the knowledge graph.
Documented attack patterns abuse exactly the kind of access create_entities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and KnowledgeGraph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_entities:
{
"version": "1",
"default": "deny",
"tools": {
"create_entities": {
"limits": [
{
"counter": "create_entities_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_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.
CREATE new entities with OBSERVATIONS and optional tags. MANDATORY: If creating multiple entities, use a SINGLE call (batch). Each entity requires a unique name, type, and at least one observation. Ignores existing names. Use search_knowledge first. It is categorised as a Write tool in the KnowledgeGraph MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KnowledgeGraph MCP Server MCP server in PolicyLayer and add a rule for create_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 KnowledgeGraph MCP Server. Nothing to install.
create_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 create_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 create_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.
create_entities is provided by the KnowledgeGraph MCP Server MCP server (n-r-w/knowledgegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from KnowledgeGraph MCP Server, 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.
11 KnowledgeGraph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.