Upload a video to an ad account. Small videos (<50MB) upload in one request. Returns the video ID.
AI agents use upload_ad_video to create or update resources in Claude Meta — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Meta environment.
The tool creates and stores new video assets in the ad account, which is a reversible modification (videos can be deleted via delete_ad_creative or account management). It does not execute arbitrary code, delete data irreversibly, or involve financial transactions. The severity is medium because misuse could result in resource waste, account spam, or content policy violations, but the action remains reversible.
From the tool's definition Tool description states 'Upload a video to an ad account' and 'Returns the video ID', indicating creation of new media assets.
Attacks that exploit this kind of access
Upload a video to an ad account. Small videos (<50MB) upload in one request. Returns the video ID. It is categorised as a Write tool in the Claude Meta MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Meta MCP server in PolicyLayer and add a rule for upload_ad_video: 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 Claude Meta. Nothing to install.
upload_ad_video 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_ad_video 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_ad_video. 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_ad_video is provided by the Claude Meta MCP server (maxx3250/claude-meta-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 →