What is the Model Context Protocol?

Definition

The Model Context Protocol (MCP) is an open standard that lets AI applications connect to outside systems in a consistent way. Its own documentation calls it "an open-source standard for connecting AI applications to external systems."

In practice, an MCP connection lets an assistant such as Claude or ChatGPT read from, and sometimes act in, tools like a CRM or a notetaker, using permissions you grant.

Why it matters for advisors

Several advisor-tech vendors now offer MCP connections, which can make a general assistant much more useful: it can pull a client's CRM history into a meeting prep request, for example.

It also opens a new data path. Client information can flow from your CRM into the assistant, so the assistant's plan and data terms now matter as much as the CRM's. Review what each connection can read and write before turning it on.

Example

A firm connects its CRM to an approved enterprise AI assistant with read-only access, so advisors can ask for meeting prep, but the assistant can't change records.

Watch out for

A connection is only as safe as the least-protected tool in the chain. Don't connect firm systems to a personal or unapproved AI account.