Upload an image to Google Files API for use as reference, first frame, or last frame in video generation. Returns a fileUri that can be reused for 48 hours. This is the most token-efficient way to pass images to video generation.
AI agents use upload_image to create or update resources in Veo 3 1 MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Veo 3 1 MCP Server environment.
This tool creates/uploads data to a cloud storage service (Google Files API). While it modifies state by adding a new file, the action is reversible (the file can be deleted). It does not execute arbitrary code, delete data irreversibly, or move money. It therefore falls under Write rather than Execute or Destructive.
From the tool's definition Tool 'upload_image' with description stating 'Upload an image to Google Files API' — performs a create/upload operation that stores data reversibly in Google's file system.
Attacks that exploit this kind of access
Upload an image to Google Files API for use as reference, first frame, or last frame in video generation. Returns a fileUri that can be reused for 48 hours. This is the most token-efficient way to pass images to video generation. It is categorised as a Write tool in the Veo 3 1 MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Veo 3 1 MCP Server MCP server in PolicyLayer and add a rule for 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 Veo 3 1 MCP Server. Nothing to install.
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 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 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.
upload_image is provided by the Veo 3 1 MCP Server MCP server (waimakers/veo-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 →