#AI55 discussing

Hi @Dan Humphries,

This is not available out of the box. The Salesforce hosted MCP tools work on records (SOQL and sObject reads). Files are stored in ContentVersion, and the actual content sits in the binary field VersionData. Claude can find the file, but it cannot read the text inside a PDF or Word doc.

Practical workaround:

1. Download the file with the REST API (/sobjects/ContentVersion/<id>/VersionData).
2. Extract the text with an external script or service (for example Python).
3. Save the text in a Long Text Area field on the Opportunity, or in a custom object.
4. Claude can then read that field through MCP like any normal field.

You can also build a Flow or Apex action that returns this text, and expose it as an MCP tool.

Official docs:

• Hosted MCP servers overview: https://developer.salesforce.com/docs/platform/hosted-mcp-servers/guide/hosted-mcp-servers-overview.html
• Server reference (list of tools): https://developer.salesforce.com/docs/platform/hosted-mcp-servers/references/reference/servers-reference.html
• sObject server details: https://developer.salesforce.com/docs/platform/hosted-mcp-servers/references/reference/sobject-all.html

@pankaj singh @Jonathan Green @Nyjil K J @Asim Ansari @Nicholas Skaggs

I am the Product Manager for Builder Central. Can you please check if your org is on Winter '27? Builder Central requires the orgs to be on Winter '27.  

If your org is on Winter '27, can you please email me your org details and user details at

Hi Chromer, This error usually happens when Salesforce doesn't allow changes to the current agent version. 

Try these steps:

1. Check if the agent is active. Deactivate it before making changes.
2. Refresh Agent Builder and try publishing again.
3. Check if any deployment or publishing process is still running.
4. If possible, try creating the agent again in a fresh Trailhead org.
5. If the issue continues, raise a Trailhead support case with the error and request ID.

It could also be a temporary Salesforce platform issue.

Hope this helps!

Hi @Santhosh Gorantala

This is a common challenge when customer data comes from multiple systems.

I would normally start by checking the match rules and source data quality.

A few things I would suggest:

1. Match Rules: Check whether the rules are too strict. Sometimes small differences in names, emails, or phone numbers prevent matching.
2. Data Quality: Look for missing values, duplicate records, extra spaces, and inconsistent formats.
3. Normalization: Try normalized email and phone matching where applicable.
4. Data Mapping: Make sure Individual, Contact Point Email, and Contact Point Phone are mapped correctly, including their relationships.
5. Ruleset Execution: Check whether the Identity Resolution ruleset completed successfully and review the processing results.
6. Reconciliation Rules: If records are unified but the expected field values aren't showing, check which source is given priority.

Simple Example:

One system has "Santhosh Kumar" and another has "Santosh Kumar". An exact name match may fail, but fuzzy matching could help identify them as the same person. 

My suggestion is to take 2–3 customer records that should match, compare their source values, and test the matching rules step by step. 

One important point: Match rules decide which records get unified, while reconciliation rules decide which field values appear in the unified profile.

Hope this helps! 

Thank you, 

Venkat Yadav.

Hi @Santhosh Gorantala

Good question! I think the main thing is to include only the data that Agentforce actually needs, rather than bringing everything into one Data Graph. 

A few things I would consider:

1. Business Use Case: First, understand what questions the agent needs to answer and what data is required.
2. Relevant Data: Include only necessary objects and fields. Avoid adding unnecessary information.
3. Relationships: Keep relationships simple. Too many related objects can make things complex.
4. Data Volume: Be careful with large datasets and historical records.
5. Performance: Test how quickly Agentforce can retrieve the required information.

For example, if we're building a customer support agent, I would start with Account, Contact, recent Cases, and Orders instead of bringing in the entire customer history.

And yes, adding too many related objects or attributes can increase graph size and potentially impact performance. 

My suggestion would be to start small, test with real-world scenarios, and add more data only when it's actually needed. 

At the end of the day, Agentforce needs the right information at the right time, not every piece of data available. 

Hope this helps! 

Thank you, 

Venkat Yadav.

Hi @Chandra Shekar

Good question! Trailhead is a great place to learn Salesforce, but working on complete projects will help you understand how things work in real companies. 

Here are a few things I would suggest:

1. Build Real-Time Projects: Start with projects like Student Management, Recruitment Management, or Customer Support Management.
2. Understand Requirements: Don't just create objects and fields. Think about the actual business problem you're trying to solve.
3. Practice Admin & Development: Work with security, Flows, validation rules, Apex, SOQL, and LWC based on project requirements.
4. Work on Real Scenarios: Practice bulk data uploads, error handling, record sharing, and approval processes.
5. Use GitHub: Upload your project code, requirements, screenshots, and documentation.
6. Join the Community: Participate in Salesforce community discussions, developer groups, and hackathons.
7. Practice Team Work: Learn how Jira, Agile, Scrum, Git, and deployment processes work.

My suggestion:

 Pick one project and complete it from requirement gathering to development, testing, and deployment. 

For example, build a Recruitment Management application where recruiters can manage candidates, schedule interviews, and track hiring status. 

Most importantly, during interviews, you should be able to explain what you built, why you built it, and how you solved the challenges. 

A complete hands-on project can give you much better practical understanding than completing multiple Trailhead modules alone.

Hope this helps!