← Back
Towards Data Science

How to Design MCP Servers That Leave Orchestration to the Host

•
#mcp
Level:Intermediate
For:AI Engineers
✦TL;DR

The article presents a Python SDK v2 catalogue server that implements a Model Context Protocol (MCP) server exposing two narrow tools, a single resource, and one prompt, deliberately keeping planning, workflow state, and authorisation on the host side. This design demonstrates how MCP servers can offload orchestration responsibilities to the host application, simplifying server logic. Engineers can adopt this pattern to build lightweight MCP services that integrate cleanly with existing host‑side orchestration frameworks.

⚡ Key Takeaways

  • The MCP server exposes **two narrow tools**, **one resource**, and **one prompt**.
  • Server design keeps **planning, workflow state, and authorisation** on the host side.
  • This approach reduces server complexity and shifts orchestration overhead to the host.
  • Integration uses the **Python SDK v2 catalogue server** as the implementation surface.
  • Requires the host application to manage orchestration, state, and auth logic.

🔧 Tools & Libraries

Python SDK v2
💡 Why It Matters

By moving orchestration to the host, engineers can deploy minimal MCP servers that are easier to maintain and scale, while leveraging existing host‑side workflow engines for complex control flow.

✅ Practical Steps

  1. Deploy a **Python SDK v2 catalogue server** configured with two narrow tools, one resource, and one prompt as described.
  2. Implement host‑side orchestration to handle planning, workflow state, and authorisation for the MCP interactions.
  3. Connect your host application to the MCP server using the SDK’s client interfaces to invoke the defined tools and prompts.

Want the full story? Read the original article.

Read on Towards Data Science ↗

More like this

Govern and discover records with common metadata in AWS Agent Registry

AWS ML Blog•#mcp

Automating AWS Agent Registry updates with push-based architecture

AWS ML Blog•#mcp

Serverless MCP server for AI agent data lake access on Amazon ECS Fargate

AWS ML Blog•#mcp

Workflow context for AI agents with Smartsheet MCP on AWS

AWS ML Blog•#mcp

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING