AI agents use 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 a remote registry and writes it to local storage. It creates/modifies local data (adds a new model) but is reversible (the model can be deleted). It does not execute code or irreversibly destroy data, placing it in the Write category. Severity is medium because pulling arbitrary models from a registry could introduce untrusted model weights into the local environment.
From the tool's definition Pull a model from a registry
Documented attack patterns abuse exactly the kind of access pull gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ollama MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for pull:
{
"version": "1",
"default": "deny",
"tools": {
"pull": {
"limits": [
{
"counter": "pull_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}pull 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.
Pull a model from a registry. 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 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.
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 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 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.
pull is provided by the Ollama MCP Server MCP server (nighttrek/ollama-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Ollama MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Ollama MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.