Hello all! Has anyone managed to set up the Salesforce MCP with Claude so that it can read documents, such as PDFs and Word docs, stored in Salesforce?
Example usecase - I have docs stored in opportunties (notes & attachments) I'd like to query in Claude.
I don't believe this is available out of the box, so any tips / workarounds are appreciated!
Many thanks.
#AI #Salesforce Admin
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:
- Download the file with the REST API (/sobjects/ContentVersion/<id>/VersionData).
- Extract the text with an external script or service (for example Python).
- Save the text in a Long Text Area field on the Opportunity, or in a custom object.
- 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
