Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Passtrami now supports approving Apple Password access with your iPhone FaceID instead of MacBook TouchID Allows access to Apple Passwords both via MCP and cli (MCP won't leak password into session transcript)

Sash Zats

4,130 subscribers

13,638 views • 28 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 Comments

Sash Zats28 days ago

I am still figuring out how to get iOS app approved: - macOS app is distributed outside of AppStore - the only reasonable way for iOS client is via AppStore - Apple isn't exactly known for the love of opening their walled gardens Any ideas folks have are welcome! For the adventurous souls: just build the iOS app from the repo, and pair with macOS app

Nick Farina28 days ago

Very cool!

Sash Zats28 days ago

filed under "apple should sherlock this asap"

Nick Farina28 days ago

Sigh…Apple could do a wonderful and actually-secure implementation of AI-driven password filling, monitored or unmonitored. Probably will, at some point, but it'll take them forever.

Archit Garg28 days ago

Wow! How did you do that?

Monter28 days ago

This is the kind of auth detail that decides if I let an agent touch real workflows. Does FaceID approve each secret request or the whole session?

Sash Zats27 days ago

Each one of you choose to, I haven’t implemented --yolo yet 🙂

Related Videos

1Password has a clever MCP allowing to get passwords without revealing them in plain text leaking into the agent session transcript Of course Apple Passwords does provide MCP, that is until now Passtrami is a macOS app providing MCP. It works with any agents such as codex, claude code, cursor etc. You are still in charge approving each password with TouchID

1Password has a clever MCP allowing to get passwords without revealing them in plain text leaking into the agent session transcript Of course Apple Passwords does provide MCP, that is until now Passtrami is a macOS app providing MCP. It works with any agents such as codex, claude code, cursor etc. You are still in charge approving each password with TouchID

Sash Zats

52,455 views • 29 days ago

How to connect Agent Wallet to your AI agent. → MCP: add our MCP server to Claude, sign in with District Pass. → CLI: install the fdx CLI, sign up or log in via email OTP, run in Claude Code. Now your AI agent doesn't just talk. It pays, swaps, and earns. Get Started →

How to connect Agent Wallet to your AI agent. → MCP: add our MCP server to Claude, sign in with District Pass. → CLI: install the fdx CLI, sign up or log in via email OTP, run in Claude Code. Now your AI agent doesn't just talk. It pays, swaps, and earns. Get Started →

Finance District

18,289 views • 3 months ago

X just made itself plug straight into AI tools with MCP servers. Your agents can now search and post on X directly. Not only read about it. Grok Build, Cursor, Claude, VS Code. All in. What you get: * X MCP; search posts, trends, bookmarks, even publish Articles * Docs MCP; API docs inside your workflow, no tab switching Setup is straightforward: * Go to create an X app * Enable OAuth 2.0; required for authentication * Add redirect URI; * Copy your CLIENT_ID and CLIENT_SECRET * Plug those into your MCP client or config * Run the setup commands; connect X MCP and Docs MCP * Log in once via browser; approve access * Verify; run grok mcp doctor xapi and grok mcp list Log in once. Done. Your workflow now includes X itself. X

X just made itself plug straight into AI tools with MCP servers. Your agents can now search and post on X directly. Not only read about it. Grok Build, Cursor, Claude, VS Code. All in. What you get: * X MCP; search posts, trends, bookmarks, even publish Articles * Docs MCP; API docs inside your workflow, no tab switching Setup is straightforward: * Go to create an X app * Enable OAuth 2.0; required for authentication * Add redirect URI; * Copy your CLIENT_ID and CLIENT_SECRET * Plug those into your MCP client or config * Run the setup commands; connect X MCP and Docs MCP * Log in once via browser; approve access * Verify; run grok mcp doctor xapi and grok mcp list Log in once. Done. Your workflow now includes X itself. X

Mario Nawfal

59,976 views • 3 months ago

Ship your API to every MCP client in minutes 🚢 Upload your OpenAPI spec to Stainless → Generate an MCP Server → Your users can access your API in Claude Code Community, Cursor, and VS Code Watch me use the Replicate MCP Server to create a logo for my upcoming AI Podcast Generator, all with a single prompt! Now any MCP client can generate images and videos directly

Adam Anzuoni

22,423 views • 1 year ago

A day of research now takes minutes with MCP Teams using AI get it: speed + scalable intel win. So we built this. Get direct AI access to full CryptoRank data via MCP. No code / No manual wrangling / No lost time

A day of research now takes minutes with MCP Teams using AI get it: speed + scalable intel win. So we built this. Get direct AI access to full CryptoRank data via MCP. No code / No manual wrangling / No lost time

CryptoRank.io

22,010 views • 7 months ago

Your entire n8n instance is now MCP-ready. Access your workflows through native connectors in Lovable and Mistral AI, with Claude and more platforms on the way! Give it a try with n8n version 1.121.2 and your go-to MCP-enabled platform. 🔗 Watch the full video here:

Your entire n8n instance is now MCP-ready. Access your workflows through native connectors in Lovable and Mistral AI, with Claude and more platforms on the way! Give it a try with n8n version 1.121.2 and your go-to MCP-enabled platform. 🔗 Watch the full video here:

n8n.io

24,395 views • 10 months ago

here's a under the hood look at something we're working on to enable an even easier sign-in experience for our new coinbase cli/mcp access from all major web and local agent harnesses sign-in-with-coinbase (instead of API keys) coming soon!

here's a under the hood look at something we're working on to enable an even easier sign-in experience for our new coinbase cli/mcp access from all major web and local agent harnesses sign-in-with-coinbase (instead of API keys) coming soon!

lincoln.base.eth

48,032 views • 3 months ago

Wazabi AI MCP now supports Openτensor Foundaτion subnet creation (beta). Quote burn cost → prepare subnet → sign with your wallet → live on-chain. All from Claude Cursor or any MCP-compatible AI IDE. No CLI scripts. Inviting the Bittensor community to test it out and give us feedback. Mainnet + testnet supported.

Wazabi AI MCP now supports Openτensor Foundaτion subnet creation (beta). Quote burn cost → prepare subnet → sign with your wallet → live on-chain. All from Claude Cursor or any MCP-compatible AI IDE. No CLI scripts. Inviting the Bittensor community to test it out and give us feedback. Mainnet + testnet supported.

Wazabi AI

11,227 views • 6 months ago

Introducing Motion UI. White label, production-ready, performance-graded UI components for React. Ready to drop straight into your design via shadcn CLI and Tailwind CSS, or adapt via your agent with our one-click prompt generator or the Motion MCP.

Introducing Motion UI. White label, production-ready, performance-graded UI components for React. Ready to drop straight into your design via shadcn CLI and Tailwind CSS, or adapt via your agent with our one-click prompt generator or the Motion MCP.

Motion

176,347 views • 2 months ago

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 views • 1 year ago

GPT-5.6 is scary good at making ads 🤯, paired with Creatify's MCP, you can turn ideas into finished ads in minutes. The same reasoning that powers its knowledge work now powers your ads. Whichever agent you run, Creatify's MCP gives it full access to your ad creation stack. Videos on demand, brand context baked in, and your skills ready to go.

Creatify AI

63,053 views • 3 months ago

GMT Pay is here! 💳✨ Transform your crypto into real-world spending power with instant card activation, global access, and compatibility with Apple Pay & Google Pay. Download now ⤵️

GMT Pay is here! 💳✨ Transform your crypto into real-world spending power with instant card activation, global access, and compatibility with Apple Pay & Google Pay. Download now ⤵️

FSL Ecosystem

33,893 views • 1 year ago

We know today's developers don't want to deal with endless deployment configs and infrastructure headaches. But convenience should never come at the cost of security. So we designed the next era of deployments: MCP Access Control. Introducing OpenShip MCP Access Control. Let Claude or any MCP compatible agent deploy your apps while you stay fully in control. Give your agent only the permissions it needs: • Deploy specific repositories • Read-only or list-only access • Per-resource permission scopes • Fine-grained access control for every operation Get AI-powered DevOps without giving away the keys. All on your own infrastructure, for free. Just head to the MCP tab → choose your agent → add the OpenShip MCP → authenticate → select the permissions you want to grant → then simply ask it to deploy your repository. Our goal is to make OpenShip fully agent-compatible in the safest way possible. And this is just the beginning. Soon, Claude won't just deploy your apps - it'll become your DevOps engineer, managing deployments, auto-scaling, clustering, and infrastructure maintenance while you remain in complete control. OpenShip 0.5.0 also ships with major stability improvements and tons of bug fixes.

We know today's developers don't want to deal with endless deployment configs and infrastructure headaches. But convenience should never come at the cost of security. So we designed the next era of deployments: MCP Access Control. Introducing OpenShip MCP Access Control. Let Claude or any MCP compatible agent deploy your apps while you stay fully in control. Give your agent only the permissions it needs: • Deploy specific repositories • Read-only or list-only access • Per-resource permission scopes • Fine-grained access control for every operation Get AI-powered DevOps without giving away the keys. All on your own infrastructure, for free. Just head to the MCP tab → choose your agent → add the OpenShip MCP → authenticate → select the permissions you want to grant → then simply ask it to deploy your repository. Our goal is to make OpenShip fully agent-compatible in the safest way possible. And this is just the beginning. Soon, Claude won't just deploy your apps - it'll become your DevOps engineer, managing deployments, auto-scaling, clustering, and infrastructure maintenance while you remain in complete control. OpenShip 0.5.0 also ships with major stability improvements and tons of bug fixes.

OpenShip

22,443 views • 2 months ago

Studio MCP Server now supports full agentic loops, and Assistant can connect to external LLMs via Bring Your Own Key (BYOK). This allows creators to automatically edit, test, and refine their code with AI in plain language on Roblox using their preferred tools. The simple video shows a full loop with analyze, test, bug found, fix, test, pass.

Studio MCP Server now supports full agentic loops, and Assistant can connect to external LLMs via Bring Your Own Key (BYOK). This allows creators to automatically edit, test, and refine their code with AI in plain language on Roblox using their preferred tools. The simple video shows a full loop with analyze, test, bug found, fix, test, pass.

David Baszucki

245,751 views • 7 months ago

🚀 Big news: Cline just launched the MCP Marketplace -- now you can one-click install MCP servers and give Cline access to a whole new suite of tools! What's changing with the MCP Marketplace: • Browse AI capabilities like apps • One-click MCP server installation • Automatic setup and configuration • No more JSON wrestling Before: - Find GitHub repos - Read technical docs - Configure manually - Hope it works Now: - Open Cline - Browse marketplace - Click "Install" - Start using The impact: Making AI superpowers accessible to everyone, not just tech experts. Imagine giving your AI instant access to: • Web searching capabilities • Design tools integration • Code analysis powers • And much more For developers: Want to list your MCP server? Create an issue in our mcp-marketplace repo with: • GitHub repo URL • 400x400 PNG logo • Brief description The future of AI development isn't about complex integrations. It's about unlocking capabilities with a single click. Welcome to that future. 🔮

Cline

112,069 views • 1 year ago

Portkey's MCP Gateway is now GA. MCP has truly exploded. Trillions of tokens flow through our infra every month. Agents can finally do things: hit databases, trigger workflows, access internal systems. But auth is fragmented. There's no access control. And once multiple agents are involved, it's impossible to know what can access what. Today we're fixing that. One line to connect any MCP server. Centralized authentication. Fine-grained access control by team, by tool, by action. Full observability on every tool call. Platform teams can finally say yes to agents without losing sleep. Already live with Fortune 50.

Portkey's MCP Gateway is now GA. MCP has truly exploded. Trillions of tokens flow through our infra every month. Agents can finally do things: hit databases, trigger workflows, access internal systems. But auth is fragmented. There's no access control. And once multiple agents are involved, it's impossible to know what can access what. Today we're fixing that. One line to connect any MCP server. Centralized authentication. Fine-grained access control by team, by tool, by action. Full observability on every tool call. Platform teams can finally say yes to agents without losing sleep. Already live with Fortune 50.

Rohit Agarwal

175,643 views • 8 months ago

Got a chance to chat with Tim Cook about Apples 50th anniversary. What were some of your favorite Apple moments? Mine are MacBook Air envelope, colored iMacs, 1,000 songs in your pocket and of course the first iPhone ☺️

Got a chance to chat with Tim Cook about Apples 50th anniversary. What were some of your favorite Apple moments? Mine are MacBook Air envelope, colored iMacs, 1,000 songs in your pocket and of course the first iPhone ☺️

iJustine

227,516 views • 6 months ago