[FEATURE] Support MCP for Flow and Conversational Flow Agent

[akolarkunnu]

Description

[Describe what this change achieves]

Related Issues

Resolves #3807

Check List

• New functionality includes testing.
• New functionality has been documented.
• API changes companion pull request created.
• Commits are signed per the DCO using --signoff.
• Public documentation issue/PR created.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

[codecov]

Codecov Report

❌ Patch coverage is 14.75410% with 52 lines in your changes missing coverage. Please review.
✅ Project coverage is 80.11%. Comparing base (9b11665) to head (1314296).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...orithms/agent/MLConversationalFlowAgentRunner.java	0.00%	48 Missing ⚠️
.../ml/engine/algorithms/agent/MLFlowAgentRunner.java	69.23%	3 Missing and 1 partial ⚠️

Additional details and impacted files

@@             Coverage Diff              @@
##               main    #4319      +/-   ##
============================================
- Coverage     80.14%   80.11%   -0.03%     
- Complexity    10171    10172       +1     
============================================
  Files           854      854              
  Lines         44219    44237      +18     
  Branches       5113     5113              
============================================
+ Hits          35439    35442       +3     
- Misses         6630     6645      +15     
  Partials       2150     2150              

Flag	Coverage Δ
ml-commons	80.11% <14.75%> (-0.03%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[pyek-bot]

Hi @akolarkunnu, thanks for taking this up!

User experience is critical here. Flow and Conversational Flow agents execute the tools in a given sequence. With MCP, currently, we register the server via a connector and then pass that to agents during registration. This works for Chat and PER because they dynamically pick and choose which agent to execute.

However, with flow and conversational flow, we might have to surface the tools available in these MCP servers and then allow the users to register. I'm curious about the flow you have in mind with respect the agent registration.