Upload a new model
AI agents use upload_model to create or update resources in Rockfish MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rockfish MCP Server environment.
This tool creates or adds a new model to the Rockfish ML platform, which is a reversible Write operation. While uploading a model could have downstream effects if the model is subsequently used in workflows, the upload action itself is not destructive, financial, or immediately executable code.
From the tool's definition Tool name 'upload_model' and description 'Upload a new model' indicate creation/addition of a new artifact to the ML platform.
Attacks that exploit this kind of access
Upload a new model. It is categorised as a Write tool in the Rockfish MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rockfish MCP Server MCP server in PolicyLayer and add a rule for upload_model: 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 Rockfish MCP Server. Nothing to install.
upload_model 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 upload_model 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 upload_model. 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.
upload_model is provided by the Rockfish MCP Server MCP server (wolfdancer/rockfish-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 →