Software Engineering Radio - the podcast for professional software developers

SE Radio 689: Amey Desai on the Model Context Protocol

Oct 8, 2025

Amey Desai, CTO at Nexla and data systems engineer, explains the Model Context Protocol as a way to tame integration spaghetti and let LLMs orchestrate tool calls. He walks through GitHub analytics, PDF routing, and multi-agent labeling patterns. The conversation highlights emerging MCP architectures, reliability trade-offs with agent-to-agent approaches, and practical enterprise security and adoption advice.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

MCP Vs A2A: Vertical Vs Horizontal

MCP solves vertical tool integration while Google's A2A targets horizontal agent-to-agent coordination.
Amey warns A2A adds distributed-system reliability and trust challenges compared with MCP's vertical simplicity.

ANECDOTE

Auction Bidding For Tool Selection

Nexla used an auction/bidding pattern to pick the best labeling agent by cost, latency, and accuracy.
They applied the same pattern to route PDF pages to cheap parsers or expensive vision LLMs to save cost and latency.

ADVICE

Control Orchestration With Prompts And Policies

Treat prompts as formal specifications and add policy enforcement and simple ML checks in the orchestrator.
Let users choose trade-offs (speed vs quality) rather than hiding hybrid choices behind complex defaults.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Amey Desai, the Chief Technology Officer at Nexla, speaks with host Sriram Panyam about the Model Context Protocol (MCP) and its role in enabling agentic AI systems. The conversation begins with the fundamental challenge that led to MCP's creation: the proliferation of "spaghetti code" and custom integrations as developers tried to connect LLMs to various data sources and APIs. Before MCP, engineers were writing extensive scaffolding code using frameworks such as LangChain and Haystack, spending more time on integration challenges than solving actual business problems. Desai illustrates this with concrete examples, such as building GitHub analytics to track engineering team performance. Previously, this required custom code for multiple API calls, error handling, and orchestration. With MCP, these operations can be defined as simple tool calls, allowing the LLM to handle sequencing and error management in a structured, reasonable manner.

The episode explores emerging patterns in MCP development, including auction bidding patterns for multi-agent coordination and orchestration strategies. Desai shares detailed examples from Nexla's work, including a PDF processing system that intelligently routes documents to appropriate tools based on content type, and a data labeling system that coordinates multiple specialized agents. The conversation also touches on Google's competing A2A (Agent-to-Agent) protocol, which Desai positions as solving horizontal agent coordination versus MCP's vertical tool integration approach. He expresses skepticism about A2A's reliability in production environments, comparing it to peer-to-peer systems where failure rates compound across distributed components.

Desai concludes with practical advice for enterprises and engineers, emphasizing the importance of embracing AI experimentation while focusing on governance and security rather than getting paralyzed by concerns about hallucination. He recommends starting with simple, high-value use cases like automated deployment pipelines and gradually building expertise with MCP-based solutions.

Brought to you by IEEE Computer Society and IEEE Software magazine.