Explore how the Model Context Protocol (MCP) can serve as a comprehensive solution for agent-to-agent communication in this 15-minute conference talk by Samuel Colvin, creator of Pydantic. Learn how to adapt MCP beyond its original desktop automation use case to enable autonomous agent interactions, focusing on the tool calling primitive as the most relevant feature for custom agent development. Discover MCP's key advantages over simple OpenAPI specifications, including dynamic tools that can appear and disappear based on server state, streaming logs for real-time progress updates, and the innovative sampling mechanism that allows tools to request LLM calls back through the client agent. Examine complex architectures where tools themselves are agents requiring LLM access, and understand how sampling solves the resource problem by letting tools "piggyback" on the client's LLM access rather than requiring their own. Follow a practical demonstration of a research agent using an MCP tool to query BigQuery, with detailed code walkthroughs covering Pydantic validation, automatic retries, context logging, and MCP server setup using fast_mcp. Understand the design pattern of performing inference inside tools to reduce context burden on the main agent, and observe real-world implementation through Logfire's observability platform to trace agent execution and sampling in action. Compare MCP with competing protocols like A2A and AGNTCY while exploring potential challenges, workarounds, and protocol extensions for successful agent communication systems.

Syllabus

00:00:00 - Introduction: Speaker Samuel Colvin introduces himself as the creator of Pydantic.
00:00:42 - Pydantic Ecosystem: Introduction to Pydantic the company, the Pydantic AI agent framework, and the Logfire observability platform.
00:01:18 - Talk Thesis: Explaining the title "MCP is all you need" and the main argument that MCP simplifies agent communication.
00:02:05 - MCP's Focus: Clarifying that the talk focuses on MCP for autonomous agents and custom code, not its original desktop automation use case.
00:02:48 - Tool Calling Primitive: Highlighting that "tool calling" is the most relevant MCP primitive for this context.
00:03:10 - MCP vs. OpenAPI: Listing the advantages MCP has over a simple OpenAPI specification for tool calls.
00:03:21 - Feature 1: Dynamic Tools: Tools can appear and disappear based on server state.
00:03:26 - Feature 2: Streaming Logs: The ability to return log data to the user while a tool is still executing.
00:03:33 - Feature 3: Sampling: A mechanism for a tool server to request an LLM call back through the agent client.
00:04:01 - MCP Architecture Diagram: Visualizing the basic agent-to-tool communication flow.
00:04:43 - Complex Architecture: Discussing scenarios where tools are themselves agents that need LLM access.
00:05:24 - Explaining Sampling: Detailing how sampling solves the problem of every agent needing its own LLM by allowing tools to "piggyback" on the client's LLM access.
00:06:42 - Pydantic AI's Role in Sampling: How the Pydantic AI library supports sampling on both the client and server side.
00:07:10 - Demo Start: Beginning the demonstration of a research agent that uses an MCP tool to query BigQuery.
00:08:23 - Code Walkthrough: Validation: Showing how Pydantic is used for output validation and automatic retries model_retry.
00:09:00 - Code Walkthrough: Context Logging: Demonstrating the use of mcp_context.log to send progress updates back to the client.
00:10:51 - MCP Server Setup: Showing the code for setting up an MCP server using fast_mcp.
00:11:54 - Design Pattern: Inference Inside the Tool: Explaining the benefit of having the tool perform its own LLM inference to reduce the context burden on the main agent.
00:12:27 - Main Application Code: Reviewing the client-side code that defines the agent and registers the MCP tool.
00:13:16 - Observability with Logfire: Switching to the Logfire UI to trace the execution of the agent's query.
00:14:09 - Observing Sampling in Action: Pointing out the specific span in the trace that shows the tool making an LLM call back through the client via sampling.
00:14:48 - Inspecting the SQL Query: Showing how the observability tool can be used to see the exact SQL query that was generated by the internal agent.
00:15:15 - Conclusion: Final summary of the talk's points.