Pull/download a model into Ollama from the registry, or import a local GGUF file. Use this to make additional models available for delegation. For GGUF files, create an Ollama Modelfile first, then use
AI agents use local_pull to create or update resources in Mcp Ollama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ollama environment.
The tool performs a write operation by downloading and registering new models into the local Ollama registry. While it doesn't delete or execute arbitrary code directly, it modifies the system state by adding new model artifacts that could be delegated to subsequent operations. Confidence is slightly reduced (0.85 vs.
From the tool's definition Tool description states 'Pull/download a model into Ollama from the registry, or import a local GGUF file. Use this to make additional models available' — this creates/adds new resources to the Ollama system.
Attacks that exploit this kind of access
Pull/download a model into Ollama from the registry, or import a local GGUF file. Use this to make additional models available for delegation. For GGUF files, create an Ollama Modelfile first, then use. It is categorised as a Write tool in the Mcp Ollama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ollama MCP server in PolicyLayer and add a rule for local_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 Mcp Ollama. Nothing to install.
local_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 local_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 local_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.
local_pull is provided by the Mcp Ollama MCP server (true-alter/mcp-ollama). 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 →