upload_ad_image
AI agents use upload_ad_image to create or update resources in KonQuest Meta Ads MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KonQuest Meta Ads MCP environment.
Upload operations create or persist data reversibly (images can be deleted or replaced). Within the context of a Meta Ads management system with sibling tools like create_ad_creative and create_campaign, this tool modifies advertising assets. While not destructive (data is not irreversibly deleted), it is a write operation that adds new assets to the campaign structure.
From the tool's definition Tool name is 'upload_ad_image'; it uploads (creates/stores) media content to Meta Ads system. Description is empty, limiting specificity.
Attacks that exploit this kind of access
upload_ad_image. It is categorised as a Write tool in the KonQuest Meta Ads MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KonQuest Meta Ads MCP server in PolicyLayer and add a rule for upload_ad_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 KonQuest Meta Ads MCP. Nothing to install.
upload_ad_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_ad_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_ad_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_ad_image is provided by the KonQuest Meta Ads MCP server (brandu-mos/konquest-meta-ads-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 →