正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Meet Jan-nano, a 4B model that outscores DeepSeek-v3-671B using MCP. It's built on Qwen3-4B with DAPO fine-tuning, it handles: - real-time web search - deep research Model + GGUF: To run it locally: - Install Jan Beta: - Download Jan-nano in Jan Hub - Settings -> MCP, enable MCP... show more

Menlo Research

4,807 subscribers

56,600 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术教育

Anya Rossi• Live Now

Private livecam show

6 条评论

👋 Jan 的头像

👋 Jan1 年前

yay, Jan is getting an agentic model!

Alan Dao 的头像

Alan Dao1 年前

Much more chill than mine, love it!

Louis Le 的头像

Louis Le1 年前

Yayyyy!

Regi Kusumaatmadja 的头像

Regi Kusumaatmadja1 年前

Settings -> MCP, enable MCP is not available on Jan v0.5.17?

Jonathan Rose Dunlap 的头像

Jonathan Rose Dunlap1 年前

Very cool! I couldn't get Jan to work with Ollama using the OpenAI adapter with the local address. Is support coming soon?

Dr. Daniel Bender 的头像

Dr. Daniel Bender1 年前

Congrats to the model launch! Which browser MCP did you use? Which system prompt? Asking because my brave-search MCP results with basic prompts where not always good. 🤔

相关视频

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

👋 Jan

690,853 次观看 • 1 年前

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

👋 Jan

17,759 次观看 • 11 个月前

Introducing a brand new way to use Jan 💛 You can now search the web, do deep research, and let Jan use your browser. Powered by Jan-v2-VL-Max, 30B model beating Gemini 2.5 Pro & DeepSeek R1 on execution benchmarks. Try it:

👋 Jan

29,403 次观看 • 8 个月前

Introducing Jan-v2-VL, a multimodal agent built for long-horizon tasks. Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2. It achieves longer, stable task execution in your browser without accuracy loss. 3 variants are available: - Jan-v2-VL-low (efficiency-oriented) - Jan-v2-VL-med (balanced) - Jan-v2-VL-high (deeper reasoning and longer execution) Models: To use it, update your Jan App and download Jan-v2-VL from the Model Hub. Activate Browser MCP servers for agentic use cases. Credit to the Qwen team for Qwen3-VL-8B-Thinking base model.

Introducing Jan-v2-VL, a multimodal agent built for long-horizon tasks. Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2. It achieves longer, stable task execution in your browser without accuracy loss. 3 variants are available: - Jan-v2-VL-low (efficiency-oriented) - Jan-v2-VL-med (balanced) - Jan-v2-VL-high (deeper reasoning and longer execution) Models: To use it, update your Jan App and download Jan-v2-VL from the Model Hub. Activate Browser MCP servers for agentic use cases. Credit to the Qwen team for Qwen3-VL-8B-Thinking base model.

👋 Jan

130,234 次观看 • 9 个月前

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

142,137 次观看 • 1 年前

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇

YanXbt

32,680 次观看 • 2 个月前

HERMES AGENT JUST GOT A RESEARCH BRAIN. connect it to NotebookLM and it becomes a 247 research system that builds knowledge over time. it resources. connects ideas across sources. uses that context in every real task. setup in 4 steps: 1. install Hermes with MCP enabled 2. download NotebookLM skill from GitHub 3. add endpoint to MCP servers in config 4. restart Hermes what your agent can now do: → query your notebooks instead of the open web → connect ideas across multiple sources → build knowledge session after session → use your curated context in every /goal → zero hallucinations from your own verified sources ask it anything — it answers from what YOU already know. full setup guide — MCP, models, use cases — in the article 👇

HERMES AGENT JUST GOT A RESEARCH BRAIN. connect it to NotebookLM and it becomes a 247 research system that builds knowledge over time. it resources. connects ideas across sources. uses that context in every real task. setup in 4 steps: 1. install Hermes with MCP enabled 2. download NotebookLM skill from GitHub 3. add endpoint to MCP servers in config 4. restart Hermes what your agent can now do: → query your notebooks instead of the open web → connect ideas across multiple sources → build knowledge session after session → use your curated context in every /goal → zero hallucinations from your own verified sources ask it anything — it answers from what YOU already know. full setup guide — MCP, models, use cases — in the article 👇

YanXbt

187,518 次观看 • 3 个月前

"I built a $250,000 SaaS in 4 months with AI and barely knew how to code." I'm starting to think that a coding ide like cursor/windsurf can become the everything app for creators this custom mode wrote a linkedin post that reads better than tools charging $50+ a month it can do it's own research using web searches or using the brave mcp with a free api key it's not hard to imagine that I could also hook this up to an mcp to create posts on linkedin and have my publishing schedule managed from a json file inside cursor yes, linkedin is cringe, but this is just the beginning of what will be possible soon i'm not gonna say that mcp is "wild" or "this changes everything" but it's quite exciting to see how this is going to be used

"I built a $250,000 SaaS in 4 months with AI and barely knew how to code." I'm starting to think that a coding ide like cursor/windsurf can become the everything app for creators this custom mode wrote a linkedin post that reads better than tools charging $50+ a month it can do it's own research using web searches or using the brave mcp with a free api key it's not hard to imagine that I could also hook this up to an mcp to create posts on linkedin and have my publishing schedule managed from a json file inside cursor yes, linkedin is cringe, but this is just the beginning of what will be possible soon i'm not gonna say that mcp is "wild" or "this changes everything" but it's quite exciting to see how this is going to be used

Ian Nuttall

25,647 次观看 • 1 年前

Introducing Open MCP Client 🪁 Chat with any MCP server in your own app, just grab a URL from . The team and I vibe coded with Cursor this weekend and built: 1. The first web-based MCP client (link👇) 2. An open-source client you can add into any app How it's built It uses CopilotKit🪁 for the client and interactivity layer, and connects to a 40 line LangGraph ReAct agent that coordinates MCP calls. Hosted on Vercel. Kudos to Suhas Deshpande and Tyler Slaton for hacking and thanks to Harrison Chase for pointers!

Introducing Open MCP Client 🪁 Chat with any MCP server in your own app, just grab a URL from . The team and I vibe coded with Cursor this weekend and built: 1. The first web-based MCP client (link👇) 2. An open-source client you can add into any app How it's built It uses CopilotKit🪁 for the client and interactivity layer, and connects to a 40 line LangGraph ReAct agent that coordinates MCP calls. Hosted on Vercel. Kudos to Suhas Deshpande and Tyler Slaton for hacking and thanks to Harrison Chase for pointers!

Atai Barkai

299,864 次观看 • 1 年前

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇

Taranjeet

472,126 次观看 • 1 年前

🚀 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 次观看 • 1 年前

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

Andrew Ng

81,696 次观看 • 11 个月前

Today, we're supporting MCP in Flowise! There has been a lot of discussion about MCP lately. From our perspective, MCP is nothing fancy - just tools with third-party APIs or functions, wrapped under a unified protocol that can be consumed by client LLM applications. In fact, we've had something similar for a long time with Langchain Tools. However, MCP offers two key benefits: - Its open protocol isn’t limited to specific frameworks - Client applications (like us, Cursor , @windsurf , etc) can offload the burden of maintaining and updating these tools to the official MCP creators These MCP servers (a.k.a. tools) are provided to the LLM, allowing it to decide when and how to use them. This is sometimes referred to as an "agentic" approach, as opposed to a "deterministic" approach like Zapier, where each step must be explicitly mapped out. In real-world scenarios, you might find yourself needing both approaches depending on the use case. It's still early days, and it will take time for the community to establish standards. We're excited to see where this goes!

Today, we're supporting MCP in Flowise! There has been a lot of discussion about MCP lately. From our perspective, MCP is nothing fancy - just tools with third-party APIs or functions, wrapped under a unified protocol that can be consumed by client LLM applications. In fact, we've had something similar for a long time with Langchain Tools. However, MCP offers two key benefits: - Its open protocol isn’t limited to specific frameworks - Client applications (like us, Cursor , @windsurf , etc) can offload the burden of maintaining and updating these tools to the official MCP creators These MCP servers (a.k.a. tools) are provided to the LLM, allowing it to decide when and how to use them. This is sometimes referred to as an "agentic" approach, as opposed to a "deterministic" approach like Zapier, where each step must be explicitly mapped out. In real-world scenarios, you might find yourself needing both approaches depending on the use case. It's still early days, and it will take time for the community to establish standards. We're excited to see where this goes!

FlowiseAI

27,360 次观看 • 1 年前

If your MCP server has dozens of tools, it’s probably built wrong. You need tools that are specific and clear for each use case—but you also can’t have too many. This creates an almost impossible tradeoff that most companies don’t know how to solve. That’s why I interviewed my friend Alex Rattray (Alex Rattray), the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. I had him on Every 📧’s AI & I to talk about MCP and the future of the AI-native internet. We get into: • Design MCP servers to be lean and precise. Alex’s best practices for building reliable MCP servers start with keeping the toolset small, giving each tool a precise name and description, and minimizing the inputs and outputs the model has to handle. At Stainless, they also often add a JSON filter on top to strip out unnecessary data. • Make complex APIs manageable with dynamic mode. To solve the problem of how an AI figures out which tool to use in larger APIs, Stainless switches to “dynamic mode,” where the model gets only three tools: List the endpoints, pick one and learn about it, and then execute it. • MCP servers as business copilots. At Stainless, Alex uses MCP servers to connect tools like Notion and HubSpot, so he can ask questions like, “Which customers signed up last week?” The system queries multiple databases and returns a summary that would’ve otherwise taken multiple logins and searches. • Create a “brain” for your company with Claude Code. Alex built a shared company brain at Stainless by keeping Claude Code running on his system and asking it to save useful inputs—like customer feedback and SQL queries—into GitHub. Over time, this creates a curated archive his team can query easily. • The future of MCP is code execution. Instead of giving models hundreds of tools, Alex believes the most powerful setup will be a simple code execution tool and a doc search tool. The AI writes code against an API’s SDK, runs it on a server, and checks the docs when it gets stuck. This is a must-watch for anyone who wants to understand MCP—and learn how to use them as a competitive edge. Watch below! Timestamps: Introduction: 00:01:14 Why Alex likes running barefoot: 00:02:54 APIs and MCP, the connectors of the new internet: 00:05:09 Why MCP servers are hard to get right: 00:10:53 Design principles for reliable MCP servers: 00:20:07 Scaling MCP servers for large APIs: 00:23:50 Using MCP for business ops at Stainless: 00:25:14 Building a company brain with Claude Code: 00:28:12 Where MCP goes from here: 00:33:59 Alex’s take on the security model for MCP: 00:41:10

If your MCP server has dozens of tools, it’s probably built wrong. You need tools that are specific and clear for each use case—but you also can’t have too many. This creates an almost impossible tradeoff that most companies don’t know how to solve. That’s why I interviewed my friend Alex Rattray (Alex Rattray), the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. I had him on Every 📧’s AI & I to talk about MCP and the future of the AI-native internet. We get into: • Design MCP servers to be lean and precise. Alex’s best practices for building reliable MCP servers start with keeping the toolset small, giving each tool a precise name and description, and minimizing the inputs and outputs the model has to handle. At Stainless, they also often add a JSON filter on top to strip out unnecessary data. • Make complex APIs manageable with dynamic mode. To solve the problem of how an AI figures out which tool to use in larger APIs, Stainless switches to “dynamic mode,” where the model gets only three tools: List the endpoints, pick one and learn about it, and then execute it. • MCP servers as business copilots. At Stainless, Alex uses MCP servers to connect tools like Notion and HubSpot, so he can ask questions like, “Which customers signed up last week?” The system queries multiple databases and returns a summary that would’ve otherwise taken multiple logins and searches. • Create a “brain” for your company with Claude Code. Alex built a shared company brain at Stainless by keeping Claude Code running on his system and asking it to save useful inputs—like customer feedback and SQL queries—into GitHub. Over time, this creates a curated archive his team can query easily. • The future of MCP is code execution. Instead of giving models hundreds of tools, Alex believes the most powerful setup will be a simple code execution tool and a doc search tool. The AI writes code against an API’s SDK, runs it on a server, and checks the docs when it gets stuck. This is a must-watch for anyone who wants to understand MCP—and learn how to use them as a competitive edge. Watch below! Timestamps: Introduction: 00:01:14 Why Alex likes running barefoot: 00:02:54 APIs and MCP, the connectors of the new internet: 00:05:09 Why MCP servers are hard to get right: 00:10:53 Design principles for reliable MCP servers: 00:20:07 Scaling MCP servers for large APIs: 00:23:50 Using MCP for business ops at Stainless: 00:25:14 Building a company brain with Claude Code: 00:28:12 Where MCP goes from here: 00:33:59 Alex’s take on the security model for MCP: 00:41:10

Dan Shipper 📧

15,645 次观看 • 11 个月前

Stop paying $20–50/month for your AI agent to browse the web. i built the free version no API keys, no config, no rate limits😳 it's called Hound. An MCP server that does fetch, search, crawl, and screenshot — all keyless and now it ships a native Pi extension, so you get all 6 tools as first-class Pi tools, not through a generic MCP adapter what you get: → web_fetch — anti-bot fetch → clean markdown. PDFs get section maps + auto-OCR. Dead pages auto-recover from the Internet archive (honestly marked, never pretending it's live) → web_search — 10 keyless backends in parallel (DuckDuckGo, Brave, Mojeek, Yandex, Google…) + a local neural reranker → web_crawl — best-first same-domain walk. sitemap mode maps a whole site in one fetch → web_screenshot — anti-bot shots for multimodal models → cache_clear + hound_version what it replaces: -tavily — free tier -firecrawl — $16–50/mo -searXNG + browser + extractor glue — fragile -hound — $0, keyless, forever why it matters: >agent research needs web access, but everyone gates it behind a key or a limit >hound is honest about errors — a 404 says "Page doesn't exist" instead of dumping an error page as if it were content >archive recovery tags source= so the agent knows the content is historical, not live 2-minute setup: -pip install hound-mcp[all] -pi install npm: @houndmcp/hound-mcp-pi -/reload → tools are live. That's it Caveats (read): dataDome, Akamai, Cloudflare Turnstile — no free tool bypasses these hound tries the stealthy browser, then tells you to switch sources the [all] extra is ~100MB (onnxruntime + OCR). Works without it, but full install is recommended not a scraping-at-scale tool. Crawl caps at 100 pages by default — built for agent research Give your agent the web for free

Stop paying $20–50/month for your AI agent to browse the web. i built the free version no API keys, no config, no rate limits😳 it's called Hound. An MCP server that does fetch, search, crawl, and screenshot — all keyless and now it ships a native Pi extension, so you get all 6 tools as first-class Pi tools, not through a generic MCP adapter what you get: → web_fetch — anti-bot fetch → clean markdown. PDFs get section maps + auto-OCR. Dead pages auto-recover from the Internet archive (honestly marked, never pretending it's live) → web_search — 10 keyless backends in parallel (DuckDuckGo, Brave, Mojeek, Yandex, Google…) + a local neural reranker → web_crawl — best-first same-domain walk. sitemap mode maps a whole site in one fetch → web_screenshot — anti-bot shots for multimodal models → cache_clear + hound_version what it replaces: -tavily — free tier -firecrawl — $16–50/mo -searXNG + browser + extractor glue — fragile -hound — $0, keyless, forever why it matters: >agent research needs web access, but everyone gates it behind a key or a limit >hound is honest about errors — a 404 says "Page doesn't exist" instead of dumping an error page as if it were content >archive recovery tags source= so the agent knows the content is historical, not live 2-minute setup: -pip install hound-mcp[all] -pi install npm: @houndmcp/hound-mcp-pi -/reload → tools are live. That's it Caveats (read): dataDome, Akamai, Cloudflare Turnstile — no free tool bypasses these hound tries the stealthy browser, then tells you to switch sources the [all] extra is ~100MB (onnxruntime + OCR). Works without it, but full install is recommended not a scraping-at-scale tool. Crawl caps at 100 pages by default — built for agent research Give your agent the web for free

Nahid

44,380 次观看 • 1 个月前

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Superman

282,217 次观看 • 1 个月前

A builder wants to ship an agent that can search live data, use it instantly, and keep going without manual steps. That is why OptimAI Search now ships with x402, SDK, and MCP support. x402 makes access and payment seamless. SDK and MCP make integration straightforward for builders. And under the hood, OptimAI Search gives agents real-time access to huge volumes of public and social web data, structured into context they can actually use. Add Agent Marketplace on top, and domain knowledge becomes reusable: build specialized agents, publish them, and let others build on what you create. This is what search looks like in the agent-native internet. 💡Try it:

A builder wants to ship an agent that can search live data, use it instantly, and keep going without manual steps. That is why OptimAI Search now ships with x402, SDK, and MCP support. x402 makes access and payment seamless. SDK and MCP make integration straightforward for builders. And under the hood, OptimAI Search gives agents real-time access to huge volumes of public and social web data, structured into context they can actually use. Add Agent Marketplace on top, and domain knowledge becomes reusable: build specialized agents, publish them, and let others build on what you create. This is what search looks like in the agent-native internet. 💡Try it:

OptimAI Network

36,562 次观看 • 3 个月前

MCP now supports authentication using OAuth2. This is huge! I want to share a complete example (code) so you can learn how to use it. Here is the thing: You don't want to build agentic applications that access resources without proper guardrails. With authentication, you can: • Call third-party APIs on the user's behalf • Perform actions that should be traceable • Enforce different permissions for different roles Here is an MCP-based web shop demo, built with WorkOS AuthKit and Next.js. With this example, you can do the following: • Connect to an MCP server • Authenticate using AuthKit • Order a T-shirt using MCP tools • View order details if you are an admin This GitHub repository contains everything you need: The WorkOS team has one of the best authentication platforms in the world. If you haven't looked into AuthKit, take a look at the code of this demo. Thanks to the WorkOS team for sponsoring this post.

MCP now supports authentication using OAuth2. This is huge! I want to share a complete example (code) so you can learn how to use it. Here is the thing: You don't want to build agentic applications that access resources without proper guardrails. With authentication, you can: • Call third-party APIs on the user's behalf • Perform actions that should be traceable • Enforce different permissions for different roles Here is an MCP-based web shop demo, built with WorkOS AuthKit and Next.js. With this example, you can do the following: • Connect to an MCP server • Authenticate using AuthKit • Order a T-shirt using MCP tools • View order details if you are an admin This GitHub repository contains everything you need: The WorkOS team has one of the best authentication platforms in the world. If you haven't looked into AuthKit, take a look at the code of this demo. Thanks to the WorkOS team for sponsoring this post.

Santiago

33,004 次观看 • 8 个月前

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Santiago

56,815 次观看 • 1 年前