Exercise 2: Explore the Salesforce MCP Servers

In this exercise, you'll connect your org to the AIforce Playground and use Salesforce Hosted MCPs to investigate live Pronto data across storefronts, orders, customers, and reviews.

TIP

This workshop uses the Pronto sample app data model, where Storefront__c, Order__c, and Review__c are custom objects deployed in your org. This means standard MCP servers can query and act on live storefront and order data directly, with no external callout required.

Step 1: Connect Your Org to the Playground

1. In your Salesforce org, open Setup.

2. In Quick Find, enter My Domain, then select My Domain.

3. Copy your current My Domain URL.

   Use the full URL, such as https://your-domain.my.salesforce.com.

4. Open the AIforce Playground.

   The AIforce Playground is a custom chat client built for hands-on workshops. It works like ChatGPT, Claude, or Gemini, but does not require learners to bring a separate AI subscription.

5. Authenticate to the AIforce Playground using the credentials provided by the workshop instructor.

6. Click Connect.

7. Fill the connection form with these values:

   Field	Value
   Instance URL	The Salesforce My Domain URL that you just copied.
   Consumer Key	The Consumer Key from Exercise 1.
   Consumer Secret	The Consumer Secret from Exercise 1.

8. Click Connect.

   TIP

   If authentication fails with an invalid_client_id error, wait a few minutes for the External Client App to become available, then try again.

9. When prompted, authorize the app.

Step 2: Add the Salesforce MCP Servers

1. Click Add server.

2. Click Add server again.

3. Navigate to the Salesforce hosted tab.

4. Click the sobject-all tile.

5. Click Test connection and ensure that the MCP tools are found.

6. Click Add server.

7. Repeat the above steps to test then add the headless-360 tile.

   TIP

   The Playground shows the servers by their short names, sobject-all and headless-360. They are the SObject All and Headless360 (H360) MCP Server you activated in Setup.

   At this point, the AIforce Playground should look like this with both servers active:

   

Step 3: Inspect the Pronto Data Model

1. Navigate to the Chat tab.

2. Click Tools and check the HEADLESS-360 server.

   

   TIP

   If all the tools are greyed out, turn off the Auto-select tools toggle at the top of the Tools panel.

   The Headless 360 MCP Server is a general gateway to Salesforce APIs. The LLM can discover what's available in your org, then call the platform's REST APIs directly, including the describe API that returns the fields and relationships of any object, custom objects like Storefront__c included. That makes it a good fit for exploring the data model, as long as your prompt names the objects. It has no dedicated tools for records, so the LLM has to build each REST call itself. For querying and updating records in the next steps, you'll switch to SObject All, which gives the LLM a direct tool for each job.

3. Try this prompt to identify the Pronto objects and fields that matter most for storefront and order analysis:

   What Salesforce objects and fields are most relevant for understanding storefront and order activity in this org? Focus on Storefront__c, Order__c, Review__c, and Contact.

4. Try this prompt to understand which fields can explain storefront performance, order status, and customer sentiment:

   Describe the key fields on Storefront__c, Order__c, and Review__c. Call out fields that help explain storefront rating and review volume, order status, and delivery timing.

5. Review the response and note which fields the LLM chooses for the next investigation, especially Average_Review_Score__c and Total_Reviews__c on Storefront__c, and Status__c on Order__c.

Step 4: Find Storefront and Order Signals

1. Click New chat.

2. Click Tools and select the SOBJECT-ALL server.

   

3. Try this prompt to sample the storefront data before asking more targeted questions:

   Show me a sample of Storefront__c records by name, cuisine, status, average review score, and total reviews.

4. Try this prompt to find storefronts with a high volume of canceled orders:

   Which Storefront__c records have the highest number of Order__c records with a status of Canceled? Summarize why each storefront may need operational attention.

5. Try this prompt to find storefronts that look like they're struggling with customer satisfaction:

   Find storefronts with a low Average_Review_Score__c or fewer than 5 Total_Reviews__c. Pull a sample of their Review__c comments to explain your reasoning.

6. Review the response and notice how the LLM combines metadata, record filters, and business language to explain the results.

Step 5: Chain Related Records to Update an Order

1. Click New chat.

2. Run this prompt to cancel an order on behalf of a customer:

   Cancel the most recent order placed by Leola Oliva at Urban Table Uptown. Set the cancellation reason to "Customer requested cancellation, item unavailable".

   Note how the MCP tools are chained: the LLM first queries Contact and Storefront__c to resolve the two names, then queries Order__c to find the matching order, then updates that order's Status__c and Cancelation_Reason__c.

   TIP

   We'll use this same chaining pattern, resolve a name to a record, then act on it, again in the next exercise.

Step 6 (Optional): Turn Salesforce Data into Outputs

1. Click New chat.

2. Ask the LLM to create a chart from the Salesforce data it queried.

   Create a bar chart that compares Order__c volume by order status. Use the live order data you can access through Salesforce MCP tools.

3. Try a second chart prompt.

   Create a pie chart that shows Review__c count by rating, across all storefronts.

4. Try a trend-style prompt.

   Create a line chart or timeline that shows Order__c volume over time for Urban Table Downtown. Explain any spike or drop you see in the data.

5. Ask the LLM to render a PDF-style executive summary.

   Create a one-page PDF summary for a Pronto operations lead. Include the strongest and weakest performing storefronts by average review score, the most recently canceled orders, review trends, and the next questions an operations lead should ask.

6. Review the chart or PDF output and confirm that it cites live Salesforce records rather than generic advice.

Summary

• You connected the AIforce Playground to your Salesforce org with your My Domain URL and External Client App credentials.
• You used the Headless 360 MCP Server to inspect the Pronto data model.
• You used SObject All to
  • uncover storefronts with canceled orders and low review scores, all queried directly from the real, SOQL-queryable Storefront__c, Order__c, and Review__c objects.
  • chain a name lookup across Contact, Storefront__c, and Order__c into a live order update.
  • ask the LLM to turn Salesforce MCP results into charts and a PDF-style summary.

Next, you'll create your own custom MCP server for guided business actions.