Medium Risk

publish_data_product

Publish a data product to make it available for consumption.

How to control publish_data_product ↓

What publish_data_product does on SAP Business Data Cloud MCP Server

AI agents use publish_data_product to create or update resources in SAP Business Data Cloud MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SAP Business Data Cloud MCP Server environment.

Medium Risk

Why publish_data_product needs a policy

Publishing a data product is a write operation that changes its availability state. While it affects downstream consumers and has organizational impact, it is reversible (can be unpublished).

From the tool's definition Tool performs 'Publish a data product to make it available for consumption' — creates or modifies a data product's state from unpublished to published, making it accessible to consumers.

Documented attack patterns abuse exactly the kind of access publish_data_product gives an agent:

How to control publish_data_product

PolicyLayer is an MCP gateway — it sits between your AI agents and SAP Business Data Cloud MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for publish_data_product:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "publish_data_product": {
      "limits": [
        {
          "counter": "publish_data_product_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

publish_data_product 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.

  1. Create a free account and register SAP Business Data Cloud MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about publish_data_product

What does the publish_data_product tool do? +

Publish a data product to make it available for consumption. It is categorised as a Write tool in the SAP Business Data Cloud MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on publish_data_product? +

Register the SAP Business Data Cloud MCP Server MCP server in PolicyLayer and add a rule for publish_data_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 SAP Business Data Cloud MCP Server. Nothing to install.

What risk level is publish_data_product? +

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

Can I rate-limit publish_data_product? +

Yes. Add a rate_limit block to the publish_data_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.

How do I block publish_data_product completely? +

Set action: deny in the PolicyLayer policy for publish_data_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.

What MCP server provides publish_data_product? +

publish_data_product is provided by the SAP Business Data Cloud MCP Server MCP server (mariodefelipe/sap-bdc-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SAP Business Data Cloud MCP Server tool call.

Start from SAP Business Data Cloud MCP Server, 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.

7 SAP Business Data Cloud MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.