roboflow_upload_image
AI agents use roboflow_upload_image to create or update resources in Roboflow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Roboflow MCP Server environment.
Uploading images to a dataset is a write operation that creates new data. It is reversible (images can be deleted via roboflow_delete_image), so it does not qualify as Destructive. The severity is medium because misuse could pollute datasets with unwanted imagery, but the impact is scoped to the specific project and reversible.
From the tool's definition Tool name 'roboflow_upload_image' indicates creation/addition of new image data to a Roboflow project. Server description confirms the ability to 'upload and tag images'.
Attacks that exploit this kind of access
roboflow_upload_image. It is categorised as a Write tool in the Roboflow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Roboflow MCP Server MCP server in PolicyLayer and add a rule for roboflow_upload_image: 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 Roboflow MCP Server. Nothing to install.
roboflow_upload_image 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 roboflow_upload_image 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 roboflow_upload_image. 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.
roboflow_upload_image is provided by the Roboflow MCP Server MCP server (mayankd409/roboflow-mcp-server). 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 →