AI agents use create to create or update resources in Ollama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ollama environment.
This tool creates new models, which is a reversible write operation. While it modifies the system state by adding a new model artifact, it does not delete, execute arbitrary code, or trigger financial transactions. The 'remote only' constraint limits scope.
From the tool's definition Tool name 'create' combined with description 'Create a model from a base model' indicates creation of new model entities. The restriction to 'remote only, no Modelfile support' clarifies this is a creation operation without destructive capability.
Attacks that exploit this kind of access
Create a model from a base model (remote only, no Modelfile support). It is categorised as a Write tool in the Ollama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ollama MCP server in PolicyLayer and add a rule for create: 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 Ollama. Nothing to install.
create 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 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. 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 is provided by the Ollama MCP server (ollama-mcp-server). 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 →