Push a model to a registry
AI agents use ollama_push to create or update resources in Unified MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unified MCP Server environment.
This tool creates or modifies state in an external registry by uploading a model artifact. While it doesn't delete data (ruling out Destructive) or execute arbitrary code (ruling out Execute), it does irreversibly commit data to a remote system, similar to publishing.
From the tool's definition Tool name 'ollama_push' combined with description 'Push a model to a registry' indicates uploading/transferring model data to an external registry, which is a data modification and transmission action.
Attacks that exploit this kind of access
Push a model to a registry. It is categorised as a Write tool in the Unified MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unified MCP Server MCP server in PolicyLayer and add a rule for ollama_push: 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 Unified MCP Server. Nothing to install.
ollama_push 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_push 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_push. 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_push is provided by the Unified MCP Server MCP server (qingyunyupan/ollama-mcp). 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 →