Update an existing product listing. Only provided fields are changed. Authenticated. OAuth (scope products:write) preferred; api_key accepted as fallback. Only fields you pass are changed; omitted fields are preserved. Idempotent — calling twice with the same input yields the same final state. Fo...
Risk signalsAccepts URL/endpoint input (url) · Handles credentials or secrets (api_key)
Part of the Partle server.
Free to start. No card required.
AI agents use update_product to create or modify resources in Partle. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call update_product repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Partle.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"update_product": {
"limits": [
{
"counter": "update_product_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Partle policy for all 21 tools.
These attack patterns abuse exactly the kind of access update_product gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Update an existing product listing. Only provided fields are changed. Authenticated. OAuth (scope products:write) preferred; api_key accepted as fallback. Only fields you pass are changed; omitted fields are preserved. Idempotent — calling twice with the same input yields the same final state. For creating a new listing, use create_product instead. Caller must own the product. Trying to update someone else's product returns an error. Args: product_id: ID of the product to update. Get from create_product's return value, get_my_products, or search_products. name: New product name. Omit to leave unchanged. description: New description. Omit to leave unchanged. price: New price in whole currency units (e.g. 15.99 = €15.99). Max 100000. Omit to leave unchanged. currency: New currency symbol. Omit to leave unchanged. url: New merchant URL. Omit to leave unchanged. api_key: Legacy/fallback auth. Omit when using OAuth. Returns: The updated product record (full, not just the changed fields), or {"error": ...} on auth/ownership/validation failure.. It is categorised as a Write tool in the Partle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Partle MCP server in PolicyLayer and add a rule for update_product: 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 Partle. Nothing to install.
update_product 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_product 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_product. 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_product is provided by the Partle MCP server (https://partle.rubenayla.xyz/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Partle tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.