feat: refactor plan-execute agentic orchestration in custom MCP client #151
Description
Summary
Refactor the plan-execute agentic orchestration layer to run within a custom MCP (Model Context Protocol) client, replacing or augmenting the existing AgentHive framework.
Motivation
The current src/agent_hive/ plan-and-execute sequential workflow relies on bespoke orchestration logic. Moving this into a custom MCP client enables:
- Standardized tool/server communication via MCP protocol
- Better composability with existing MCP servers (IoT, utilities, etc.)
- Cleaner separation between orchestration logic and domain agent tools
Proposed Changes
- Design custom MCP client with plan-execute loop
- Map existing AgentHive planning and execution steps to MCP tool calls
- Integrate domain agents (IoT, FMSR, TSFM, WorkOrder) as MCP tool providers
- Ensure compatibility with existing benchmark evaluation pipeline (MLflow, grading strategies)
- Add/update tests for the new orchestration layer
References
- Existing orchestration:
src/agent_hive/ - MCP server work: current
mcp-refactorbranch