Skip to content
AnthropicAnthropic

Building with MCP and the Claude API

Anthropic’s Alex Albert (Claude Relations), John Welsh (Engineering, MCP team), and Michael Cohen (Engineering, Claude API team) discuss the origins of the Model Context Protocol (MCP), the open standard for connecting AI applications to external systems, best practices for getting started with MCP, and how MCP and Claude work together to enable more powerful agentic systems. 00:00 - Introductions 00:30 - What is MCP? 1:30 - The origins of MCP 2:50 - Open sourcing MCP 5:00 - Remote MCP support 6:15: MCP registries 7:40 - Favorite MCPs: Context7 & Playwright 10:40 - Using the Claude API MCP connector 11:50 - Prompt engineering with MCP 14:20 - Best practices for managing context and tools with MCP 18:20 - How John and Michael use MCP servers for project management, home automation, and more 20:00 - Understanding the “emergent” behaviors when Claude and MCP servers work together 22:50 - The future of MCP: growth of the protocol and ecosystem Learn more about MCP: https://modelcontextprotocol.io/docs/getting-started/intro Learn more about the Claude Developer Platform: https://www.claude.com/platform/api Learn more about how to write effective tools for AI agents: https://www.anthropic.com/engineering/writing-tools-for-agents

Alex AlberthostMichael CohenguestJohn Welshguest
Oct 9, 202525mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 0:30

    Meet the team and why MCP matters to everyday work

    Alex introduces the conversation with a light joke about Claude-generated Slack updates, then frames the episode: how MCP connects Claude to real tools and data. Michael and John introduce their roles on the API and MCP teams, setting up a practical, builder-focused discussion.

  2. 0:30 – 1:30

    MCP explained: giving models external context and the ability to act

    John defines MCP (Model Context Protocol) as a standard way to provide external context beyond the chat history. The core idea is letting Claude reach outside its “box” to tools and services—like the internet or booking systems—so it can take actions on a user’s behalf.

  3. 1:30 – 2:50

    Origins: avoiding re-implementing tool use across every Claude surface

    Michael explains the motivation: tool integrations were being rebuilt repeatedly across products (editor assistants, claude.ai, Claude Code, etc.). MCP emerged to unify these integrations so functionality can be implemented once and reused everywhere.

  4. 2:50 – 5:00

    Why open source MCP: one connector for many models and a healthier ecosystem

    John argues open standards prevent a world where every vendor must maintain separate connectors for each model provider. Open-sourcing MCP enables a shared ecosystem where external context access benefits everyone, accelerating adoption and long-term durability.

  5. 5:00 – 6:15

    Remote MCP support: the turning point for usability and hosted servers

    The conversation highlights remote MCP support as a major evolution. Early MCP often required users to run everything locally, which made setup clunky and blocked SaaS providers from hosting official servers; remote support made “just connect and go” realistic.

  6. 6:15 – 7:40

    MCP registries: discovering and trusting official servers

    John describes the release of a central MCP server registry plus a standard for others to extend it. This reduces reliance on random third-party connectors and enables official endpoints (e.g., GitHub) that can be plugged into Claude products via a single URL.

  7. 7:40 – 10:40

    Favorite MCP servers: Context7 for fresh docs and Playwright for real browser eyes

    Michael and John share standout MCPs. Context7 mitigates model knowledge cutoff by pulling up-to-date documentation (including emerging formats like llms.txt), while Playwright lets Claude interact with a live browser to see pages and debug UI issues via screenshots and iteration.

  8. 10:40 – 11:50

    Using MCP with the Claude API: SDK loops vs the native MCP connector

    Michael lays out two approaches for developers. You can use the MCP SDK and implement your own tool-calling loop, or use the newer native MCP connector in the Claude API, which handles server calls and tool-result feedback automatically once you provide the MCP server URL and auth.

  9. 11:50 – 14:20

    Prompt engineering for MCP: tool definitions are part of the prompt

    John emphasizes that MCP tools and servers effectively function as prompts. Tool names, descriptions, parameter labels, and examples materially change model behavior—sometimes dramatically—such as guiding Claude to write better diffusion-model prompts for image generation.

  10. 14:20 – 18:20

    Context & tool management best practices: avoid bloating and ambiguity

    Michael warns against stuffing too many MCP servers/tools into a single request, which increases token cost and can confuse the model—especially when tools overlap (e.g., Linear and Asana both having “Get Project Status”). John adds that fewer, higher-level tools often outperform large API-like tool catalogs, and the relevant subset should be loaded per task.

  11. 18:20 – 20:00

    Real-world workflows: project status automation and home automation assistants

    Michael describes using MCP to synthesize project updates by connecting Claude to internal knowledge sources (Slack, docs, code) and generating updates in his established format. John shares home-network MCP servers that let Claude check and control devices (e.g., door locks), offering a glimpse of everyday agentic computing.

  12. 20:00 – 22:50

    Emergent behaviors: unexpected capability from combining servers and intent-level tooling

    John explains “emergent” behavior when Claude can mix and match MCP servers—like linking Gmail and home automation to solve problems creatively. He also describes a knowledge-graph MCP experiment where minimal tools led Claude to adopt an investigative, memory-building interaction style, highlighting how small interfaces can shape behavior.

  13. 22:50 – 25:58

    What’s next for MCP: invisible infrastructure and competition on server quality

    The group predicts MCP’s success will make it increasingly invisible—just the connective tissue that gives apps “arms and legs.” John expects maturation in MCP server craft: evaluation-driven improvements and vendors competing on who provides the best MCP experience, making MCP support a differentiator for products like log analytics.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome