Change the visibility mode of a prepared job before pushing it to the store.
AI agents use dsers_product_visibility to create or update resources in DSers MCP Product — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DSers MCP Product environment.
This tool modifies a setting (visibility mode) on a prepared job, which is a reversible write operation. It does not delete data, execute code, or move money. Misuse could result in products being published or hidden unintentionally, but the effect is reversible.
From the tool's definition 'Change the visibility mode of a prepared job before pushing it to the store'
Attacks that exploit this kind of access
Change the visibility mode of a prepared job before pushing it to the store. It is categorised as a Write tool in the DSers MCP Product MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DSers MCP Product MCP server in PolicyLayer and add a rule for dsers_product_visibility: 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 DSers MCP Product. Nothing to install.
dsers_product_visibility 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 dsers_product_visibility 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 dsers_product_visibility. 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.
dsers_product_visibility is provided by the DSers MCP Product MCP server (oyaaiprod/dsers-mcp-product). 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 →