New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

update_openai_ads_feed_products

Update the PRICE, TITLE or AVAILABILITY of variants already in a ChatGPT Ads product feed — send only what changed instead of re-uploading the catalog. This is what stops a stale feed serving ads for out-of-stock items. Pass feedId and products:[{id, variants:[{id, title?, price?:{amount,currency...

SERVERHermoso SOURCEhttps://app.hermoso.ai/mcp
Medium RISK CLASS
Category Write
Parameters 00 required
Recommended Rate-limitedsee the rule below
Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/hermoso/update-openai-ads-feed-products.md

What update_openai_ads_feed_products does on Hermoso

AI agents use update_openai_ads_feed_products to create or update resources in Hermoso, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hermoso environment.

Why update_openai_ads_feed_products is rated Medium

An AI agent can call update_openai_ads_feed_products faster than any human can review: one bad instruction and it creates or modifies resources in Hermoso by the hundred, each call as confident as the last.

Questions about update_openai_ads_feed_products

What does the update_openai_ads_feed_products tool do? +

Update the PRICE, TITLE or AVAILABILITY of variants already in a ChatGPT Ads product feed — send only what changed instead of re-uploading the catalog. This is what stops a stale feed serving ads for out-of-stock items. Pass feedId and products:[{id, variants:[{id, title?, price?:{amount,currency}, availability?:{available|status}}]}], where products[].id is the PARENT product id and variants[].id the existing variant id, both from the catalog already in the feed. price.amount is an INTEGER IN MINOR UNITS — 8999 means $89.99 — so a decimal is a hundredfold error in the price you advertise, and is refused. IT UPDATES EXISTING VARIANTS ONLY: it never creates a feed, uploads a catalog, or adds a product that is not already there. ACCEPTED IS NOT LIVE — OpenAI applies the change asynchronously and returns no completion timestamp and no downstream result, so an out-of-stock product keeps serving until it propagates; say that rather than reporting it as done. A 403 naming product_feed_api_disabled / product_feed_delta_api_disabled means the ACCOUNT lacks Feeds access — nothing about the request was wrong and retrying it unchanged will not help. A 404 means the feed id is wrong, the feed is not linked to this ad account, or Feeds is not enabled. It is categorised as a Write tool in the Hermoso MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_openai_ads_feed_products? +

Register the Hermoso MCP server in PolicyLayer and add a rule for update_openai_ads_feed_products: 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 Hermoso. Nothing to install.

What risk level is update_openai_ads_feed_products? +

update_openai_ads_feed_products is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_openai_ads_feed_products? +

Yes. Add a rate_limit block to the update_openai_ads_feed_products 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.

How do I block update_openai_ads_feed_products completely? +

Set action: deny in the PolicyLayer policy for update_openai_ads_feed_products. 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.

What MCP server provides update_openai_ads_feed_products? +

update_openai_ads_feed_products is provided by the Hermoso MCP server (https://app.hermoso.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Hermoso, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Hermoso's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.