What is happening on July 28

The team behind MCP locked the new edition of the rulebook back on May 21. On July 28, it becomes official. That gap was on purpose: it gave everyone who builds the software kits, the SDKs, about ten weeks to get ready.

MCP stands for Model Context Protocol. It is a standard way for AI tools like Claude or ChatGPT to talk to business systems like Oracle EPM Cloud. Think of it like a power outlet: any plug fits any socket, because everyone follows the same standard. In April I shared an open source MCP server that connects Claude to Oracle EPM Cloud through the REST APIs, and many of you have used it to run business rules, check job status, and export data, just by asking in plain English.

For those of us connecting AI to Oracle EPM Cloud, three areas matter. Let's go through them one by one.

Change 1: The handshake goes away

When you hear handshake, it might sound like credentials. It is not. This has nothing to do with passwords. It is about how Claude and the MCP server start talking to each other. And for a regular user, you will not notice any difference day to day.

The old way: when Claude connects to an MCP server, the first thing it sends is a small introduction. Something like: hey, I am Claude Desktop, I run on this version, and here is what I know how to do. The server introduces itself back, and they agree on how they will interact. Everything after that rides on that first introduction, held in memory.

The old way

Connect and remember

An introductions step first: names, abilities, rulebook version. Then a session both sides remember.

Like Smart View: you connect once, everything rides that connection, and when the session expires, nothing works until you reconnect.

The new way

Every request complete

The introduction travels inside each request, next to the work details, like which business rule to run and with which parameters.

Nothing to remember, nothing to expire. Like an Oracle EPM REST call.

There is a word for this: stateless. And you already trust it every day, because the Oracle EPM REST APIs work exactly this way. No session to expire. Every call complete on its own. In one sentence: MCP is moving from the Smart View pattern to the REST pattern.

Why it matters: shared team servers

If the server does not need to remember anyone, a company can run one shared MCP server for a whole team instead of every person keeping their own copy on their own laptop. Requests from the team go through a load balancer, a kind of triage system that looks at each incoming request and decides which copy of the server should take it, based on workload. Any copy can answer any request, because every request arrives complete.

The warning that matters more than the feature

Simpler to run does not mean simpler to secure. The tempting shortcut when teams build a shared setup is to wire it up with one stored account, sometimes even admin credentials. Do that, and every person who talks to that server gets that account's access. All of it. A user who should never see workforce data. A planner who should only see the Canadian entity. With one shared admin login behind the server, they now see everything. Your entire EPM security design gets stepped over in one move.

An agent is only as safe as the login it runs under.

The safe pattern: each person connects as themselves

The right way is that each person connects as themselves, so EPM security keeps working person by person, exactly as it was designed. The new rulebook was built with this in mind. Designing it for a real company, with the right accounts, the right scopes, and the right audit trail, is real architectural design work.

And the good news: if you use the open source server the way most people do, one user, on your own computer, with your own login, nothing really changes for you. The agent can only see what you can already see.

Change 2: Logins get stronger

There is a new piece called Enterprise Managed Authorization. Your IT team approves the MCP server once, in the company identity system, something like Okta or Microsoft Entra. After that, everyone on the approved team connects with their own company login, the same login they already use every morning. No more setting things up person by person, twenty times for twenty planners. Microsoft, Okta, and Anthropic are already using this, along with a growing list of business tools.

One honest limit: this controls who can connect. What each person can see inside EPM still depends on your EPM security design, and with agents in the picture, that job matters more, not less. That is exactly what Part 2 of the Security Field Guide for Finance Leaders covers, coming next Tuesday.

Change 3: Three features are being retired

Three older parts of the rulebook, called Roots, Sampling, and Logging, are marked for retirement, with a twelve month window before removal. I checked the open source EPM server line by line: it is built on tools only and uses none of the three. If you built from my videos, this change does not affect your setup.

What you should actually do

  1. On your own computer. Keep using it as it is. When the updated software kit ships, update it, test it once, done. The step by step update video is coming.
  2. Shared team setup. Now an option: one shared MCP server for the whole team, secured through your identity system. Run it against a test environment first, and only then production.
  3. Pin your versions. Lock the exact version numbers in your setup, so nothing updates itself quietly while the ecosystem rolls out the new specification.
  4. Planning a rollout. Ask your identity team one question: does our login system support the new MCP approval feature yet?

Resources

Frequently Asked Questions

Will the new MCP specification break my existing MCP server?
For most people, no. If you run an MCP server locally with Claude Desktop, your day to day does not change. When the updated software kits (SDKs) ship, update your version, test once, and you are done. Teams running shared or remote setups should plan a short upgrade and test in a sandbox first.
What does stateless mean in the new MCP specification?
Under the old rules, the client and server exchanged an introduction once (the handshake) and both sides remembered that agreement for the whole session. Under the new rules, that introduction travels inside every request, next to the work details, so nothing depends on the server remembering anything. It is the same model Oracle EPM REST APIs already use: no session to expire, every call complete on its own.
What is Enterprise Managed Authorization in MCP?
A new extension that lets an IT team approve an MCP server once in the company identity system, such as Okta or Microsoft Entra. After that, everyone on the approved team connects with their own company login instead of setting things up person by person. It controls who can connect. What each person can see inside EPM is still governed by your EPM security design.
If my whole team shares one MCP server, can everyone see all the data?
Only if it is built the wrong way. If a shared server signs in to EPM with one stored account, every user inherits that account's access and your per person EPM security is bypassed. The safe pattern is that each person connects as themselves, so EPM applies each user's own access rules. An agent is only as safe as the login it runs under.
Is MCP safe to use with financial data in Oracle EPM?
It can be, when the identity design is right. A single user setup that runs with your own login can only see what you can already see, so EPM security keeps protecting you. Shared and enterprise setups require deliberate design: per user identity, correct scopes, and an audit trail. The new specification strengthens the login standards that make this possible.
When do I need to upgrade my MCP server for the new specification?
The new specification becomes official on July 28, 2026, and deprecated features carry a twelve month window. There is no emergency. Wait for the updated software kit, pin your current versions so nothing changes silently, then upgrade and test on your own schedule.