AI agents use update_seller to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
This tool creates or modifies seller account/profile data but does not delete or irreversibly destroy records. In the context of AP2 (Google's Agent-to-Agent Payment Protocol), updating seller information typically affects account credentials, business details, or payment configurations. The modification is reversible (further updates can correct it), so it falls under Write rather than Destructive.
From the tool's definition Tool named 'update_seller' with description 'Update seller information' — modifies existing seller data reversibly.
Documented attack patterns abuse exactly the kind of access update_seller gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for update_seller:
{
"version": "1",
"default": "deny",
"tools": {
"update_seller": {
"limits": [
{
"counter": "update_seller_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_seller stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update seller information. It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for update_seller: 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 Mcp Ap2. Nothing to install.
update_seller 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 update_seller 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 update_seller. 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.
update_seller is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.