Push a model to the Ollama registry. Uploads a local model to make it available remotely.
AI agents use ollama_push 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 creates or modifies remote state by uploading model artifacts to a registry. It is reversible (the uploaded model can be deleted or replaced), so it falls under Write rather than Destructive.
From the tool's definition Tool description states 'Uploads a local model to make it available remotely.' The term 'push' combined with 'uploads' and 'to make available remotely' indicates creation or modification of remote state through network transmission of model artifacts.
Documented attack patterns abuse exactly the kind of access ollama_push 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 ollama_push:
{
"version": "1",
"default": "deny",
"tools": {
"ollama_push": {
"limits": [
{
"counter": "ollama_push_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}ollama_push 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.
Push a model to the Ollama registry. Uploads a local model to make it available remotely. 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_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 Ollama 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 Ollama MCP Server MCP server (rawveg/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 13 Ollama MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 Ollama MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.