← All popular talks

Popular talk #27

The Future of MCP — David Soria Parra, Anthropic

Synced transcript

Follow the talk

Community discussion

Add context, evidence, or a useful disagreement

Build on the talk with an example, caveat, connection, or elaboration. Draft here, add the moment you’re discussing, then choose the direct-post pilot or the YouTube handoff.

Make it useful: add one concrete point, then support it with context, evidence, an example, or a caveat. Your words stay exactly as written.

Automated overview

What this talk covers

David Soria Parra from Anthropic argues that MCP (Model Context Protocol) is the key to connecting agents to tools and data in production, with 110 million monthly downloads—outpacing React's growth at the same stage. He lays out a 2026 connectivity stack combining Skills, MCP, and CLI/Computer Use, each suited for different needs, and emphasizes that best agents will use all three seamlessly. To improve client harnesses, he introduces Progressive Discovery—deferring tool loading via Tool Search to reduce context usage—and Programmatic Tool Calling, where models write scripts to compose tool outputs efficiently. Upcoming MCP protocol improvements include stateless transport (with Google) for easier scaling, async agent-to-agent tasks, enterprise features like Cross App Access and Server Discovery via well-known URLs, and a Skills-over-MCP extension for shipping usage instructions with servers. He calls for community feedback on these directions.

This overview is derived from the transcript and has not been independently fact-checked by AI Engineer.

Generated highlights

Key moments

  1. 0:16insightIntro

    An MCP application enables an agent to ship its own interface that works across Claude, ChatGPT, VS Code, and Cursor.

  2. 1:34storyEcosystem

    18 months ago, MCP consisted only of a spec document and locally-run SDKs largely written by Claude.

  3. 3:46predictionProduction 2026

    2025 was about exploring agents, but 2026 will be about putting them into production.

  4. 5:07insightConnectivity

    The 2026 connectivity stack for agents consists of Skills for domain knowledge, CLI for local coding, and MCP for rich semantics and enterprise.

  5. 7:47insightDiscovery

    Progressive Discovery with tool search defers tool loading to the moment a model needs it, reducing context window bloat.

  6. 12:00insightAgent Design

    Server authors should design tools for agent interaction rather than converting REST APIs one-to-one into MCP servers.

These moment labels are generated from the unreviewed transcript and may contain errors.