> For the complete documentation index, see [llms.txt](https://docs.struct.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.struct.com/tutorials/guides/how-to-use-mcp/example-of-using-mcp.md). # Example of using MCP Example of working with Struct PIM through MCP In the following example, we use Claude Desktop to check and modify product data through MCP. Claude can access the tools made available through the Struct PIM MCP configuration. You can view the available connectors by clicking the + icon and navigating to Connectors > Manage connectors.

You will then be presented with a list of available connectors.

Select the connector for the PIM MCP server to view the available tools. You will be presented with a list of the available tools and their current permission settings.

If you want to control and approve every change made in Struct PIM, you can set the relevant tool permissions to "Needs approval". This requires Claude to ask for your approval before invoking those tools. In this example, we have left the majority of the tools set to "Always allow", allowing Claude to perform the required actions without asking for user approval each time.

Claude Desktop - Connector tools set to "Always allow"

### Locating and enriching products In this example, we have a Dangerous Chemicals product structure where we want to ensure that all products of this structure have the required UN Number and Danger Classification attributes enriched with correct data. Instead of manually checking each product and adding the missing information, we ask our AI assistant to identify products with missing information and enrich them.

Here, you can see the AI using the available tools to retrieve information from the PIM. The assistant identifies products where the mentioned attributes are missing information and then enriches those products with the required data retrieved from the web.

If we look at the PIM, we can see the result of the work performed by the AI assistant.

PIM Search - Result of AI assistant work

The UN Number and Danger Classification attributes have now been correctly enriched with the required data. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.struct.com/tutorials/guides/how-to-use-mcp/example-of-using-mcp.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.