AI agents use snapix_create_gallery to create or update resources in Snapix — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Snapix environment.
snapix_create_gallery creates a new resource (a gallery) and optionally modifies the assignment of existing images to it. This is a reversible write operation — galleries can be deleted (evidenced by the sibling tool snapix_delete_gallery), making this a Write rather than Destructive action.
From the tool's definition Tool description states 'Create a new gallery' and 'Optionally assign existing images by ID.' The action is reversible creation of a data structure with no destructive operations or financial commitments.
Attacks that exploit this kind of access
Create a new gallery to organize images. Optionally assign existing images by ID. Galleries can be public (shareable) or private. Free — does not consume App credits. It is categorised as a Write tool in the Snapix MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Snapix MCP server in PolicyLayer and add a rule for snapix_create_gallery: 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 Snapix. Nothing to install.
snapix_create_gallery 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 snapix_create_gallery 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 snapix_create_gallery. 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.
snapix_create_gallery is provided by the Snapix MCP server (@metalevel/snapix-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 →