The Stack Overflow Podcast

No need for Ctrl+C when you have MCP

Ryan sits down with Member of the Technical Staff at Anthropic and Model Context Protocol co-creator David Soria Parra to talk the evolution of MCP from local-only to remote connectivity, how security and privacy fit into their work with OAuth2 for authentication and authorization, and how they’re keeping MCP completely open-source and widely available by moving it to the Linux Foundation.  Episode notes: The Model Context Protocol [https://modelcontextprotocol.io/docs/getting-started/intro] (MCP) is an open-source standard for connecting AI applications to external systems created by Anthropic [https://www.anthropic.com/]. You can keep up with—or join—the work the MCP community is doing at their Discord server [https://modelcontextprotocol.io/community/communication#discord].  Connect with David on Twitter [https://x.com/dsp_].  Today’s shoutout goes to Populist badge winner competent_tech [https://stackoverflow.com/users/1002323/competent-tech] for their answer to How do I review a PR assigned to me in VS 2022 [https://stackoverflow.com/questions/70292639/how-do-i-review-a-pr-assigned-to-me-in-vs-2022]. TRANSCRIPT [https://stackoverflow.blog/2026/03/03/no-need-for-ctrl-c-when-you-have-mcp/] See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

To live in an AI world, knowing is half the battle

Ryan welcomes Marcus Fontoura, technical fellow at Microsoft and author of Human Agency in the Digital World, to discuss the intersection of technology, society, and human dignity in a digital-first world. They chat about the non-determinism of social media algorithms, the need for balance between efficiency and human dignity in technology, and the role that trust plays in AI. Episode notes:  Human Agency in the Digital World [https://digitalagencybook.org/] is an “AI-era self-help book” about reclaiming our role as pilots—not passengers—in the technology revolution. It’s available now on Amazon [https://www.amazon.com/Human-Agency-Digital-World-Understand/dp/B0FRSS9J5G] and everywhere books are sold.  Connect with Marcus on LinkedIn [https://www.linkedin.com/in/marcusfontoura/] and learn more about his work at his website [https://fontoura.org/]. Congrats to user Romain [https://stackoverflow.com/users/1263888/romain] for winning a Populist badge on their answer to Django: show the count of related objects in admin list_display [https://stackoverflow.com/questions/32443471/django-show-the-count-of-related-objects-in-admin-list-display].  TRANSCRIPT [https://stackoverflow.blog/2026/02/27/to-live-in-an-ai-world-knowing-is-half-the-battle/] See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

Dogfood so nutritious it’s building the future of SDLCs

Ryan welcomes Thibault Sottiaux, OpenAI’s engineering lead on Codex, to discuss how the Codex team dogfoods Codex to build Codex, what distinguishes an agentic coding tool from a chat-based code assistant, and why they’re focusing on a safe and secure agentic SDLC rather than just code generation. Episode notes:  Codex CLI [https://chatgpt.com/codex] is a coding agent from OpenAI that runs locally on your computer. Try it now with your Free or Go ChatGPT plan. You can keep up with everything happening at OpenAI on their blog [https://openai.com/news/company-announcements/].  Connect with Thibault on LinkedIn [https://www.linkedin.com/in/thibault-sottiaux-27195366/] and Twitter [https://x.com/thsottiaux]. Congrats to user kevinyu [https://stackoverflow.com/users/3800474/kevinyu] for winning a Great Question badge for Does println! borrow or own the variable? [https://stackoverflow.com/questions/30450399/does-println-borrow-or-own-the-variable]. TRANSCRIPT [https://stackoverflow.blog/2026/02/24/dogfood-so-nutritious-it-s-building-the-future-of-sdlcs/] See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

Even GenAI uses Wikipedia as a source

Ryan is joined by Philippe Saade, the AI project lead at Wikimedia Deutschland, to dive into the Wikidata Embedding Project and how their team vectorized 30 million of Wikidata’s 119 million entries for semantic search. They discuss how this project helped offload the burden that scraping was creating for their sites, what Wikimedia.DE is doing to maintain data integrity for their entries, and the importance of user feedback even as they work to bring Wikipedia’s vast knowledge to people building open-source AI projects.  Episode notes:  Wikimedia.DE [http://wikimedia.de] announced the Wikidata Embedding Project [https://www.wikidata.org/wiki/Wikidata:Embedding_Project] with MCP support in October of last year. Check out their vector database [https://wd-vectordb.wmcloud.org/] and codebase [https://github.com/philippesaade-wmde/WikidataTextEmbedding] for the project.  Connect with Philippe on LinkedIn [https://www.linkedin.com/in/philippesaade1998/] and his Wiki page [https://meta.wikimedia.org/wiki/User:Philippe_Saade_(WMDE)].  Today’s shoutout goes to an Unsung Hero [https://stackoverflow.com/help/badges/226/unsung-hero] on Stack Overflow—someone who has more than 10 accepted answers with a zero score, making up 25% of their total. Thank you to user MWB [https://stackoverflow.com/users/4331279/mwb] for bringing your knowledge to the community! TRANSCRIPT [https://stackoverflow.blog/2026/02/20/even-genai-uses-wikipedia-as-a-source/] See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

Why Stack Overflow and Cloudflare launched a pay-per-crawl model

In this episode of Leaders of Code, Stack Overflow’s Janice Manningham and Josh Zhang sit down with Cloudflare VP Will Allen to discuss the innovative pay-per-crawl model co-launched by their organizations. They explore how the rise of AI has disrupted the traditional “open versus block” internet model, creating a need for platforms to protect their content and data from commercial exploitation while maintaining community access. The discussion also: * Explores the future of the bot ecosystem, emphasizing the importance of putting publishers back in the driver’s seat to decide how their content is accessed and monetized. * Explains the technical implementation of the pay-per-crawl system, which uses Cloudflare’s bot categorization and WAF rules to serve a 402 “Payment Required” message to specific crawlers. * Highlights the strategic value of data licensing, comparing comprehensive enterprise contracts with the more flexible, programmatic pay-per-use access enabled by the new model. Notes * Connect with Will Allen [https://www.linkedin.com/in/williamallen2050/], Janice Manningham [https://www.linkedin.com/in/janicemanningham/] and Josh Zhang [https://www.linkedin.com/in/josh-zhang-sre/] on LinkedIn. * Learn more about Stack Overflow Data Licensing here [https://stackoverflow.co/data-licensing/?utm_medium=podcast&utm_source=blog&utm_campaign=leaders-of-code&utm_content=pay-per-crawl-episode]. See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].