Pull (download) a model from the Ollama library.
AI agents use ollama_pull to create or update resources in Ollama MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ollama MCP Server environment.
This tool downloads a model from an external library onto the local system. It creates/adds new data (a model file) to the local Ollama instance, which is a reversible write operation (the model can later be deleted). It does not execute code, destroy data, or involve financial transactions. Misuse could involve pulling large or unintended models consuming disk space and bandwidth.
From the tool's definition Pull (download) a model from the Ollama library
Attacks that exploit this kind of access
Pull (download) a model from the Ollama library. It is categorised as a Write tool in the Ollama MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ollama MCP Server MCP server in PolicyLayer and add a rule for ollama_pull: 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 MCP Server. Nothing to install.
ollama_pull 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 ollama_pull 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 ollama_pull. 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.
ollama_pull is provided by the Ollama MCP Server MCP server (ngc-shj/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 →