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.

Hey MCP developers! Let’s talk about something broken 🧠🛠️ Agents are calling tools left and right. But what happens inside those tools? No traces. No visibility. No security. Just a black box. 🕋 The observability gap is real. Let's fix it together with observable[.]tools

Weights & Biases

48,352 subscribers

40,739 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 Comments

Weights & Biases1 year ago

We believe observability shouldn’t be a bolt-on. It should be a first-class citizen in the agent stack. So we’re launching initiative to bring full-stack tracing to MCP tools using OpenTelemetry. Think: from black boxes → glass boxes. ⎚

Weights & Biases1 year ago

To achieve this, we propose a combining OTel (open telemetry) into the official MCP protocol via a spec RFC. Combining two vendor neutral, open protocols to enable easy observability for MCP developers and tool makers (both client and server). Full proposal details on Github:

Weights & Biases1 year ago

We want to build this ecosystem together. W&B is extending an invitation to our friends from the observability industry. So... 👀 @LangChainAI, @braintrustdata, @pydantic, @arizeai, @rungalileo, @AgentOpsAI & others. Will you join this effort with us, to enable observability for the million incoming MCP developers?

Weights & Biases1 year ago

Most importantly—this is a call to YOU, the MCP tool developers. ✅ Read the manifesto 💬 Weigh in on the spec RFC 🛠️ Start building tools with observability baked in The agentic future demands transparency. Let’s build it right at

SecBriefs | Making Cybersecurity Simple1 year ago

Quantum computers can break today’s encryption in seconds.🔑 Quantum tech will reshape our digital lives. Governments & hackers are preparing for the quantum era. How about you?🛡️ Don’t get left behind!🧠 Cybersecurity Dictionary for Everyone can help:

William Horton at @PyTexas1 year ago

Why wouldn’t MCP servers just use whatever observability stack the org who built/hosts the server is using? MCP is just a certain kind of API

Weights & Biases1 year ago

Totally fair q, William. We believe agent developers need end-to-end visibility across tools. If each server logs to its own stack, there's no unified trace tree. Our approach keeps server setup simple and gives the client full control of observability.

Fadi "Ali"1 year ago

Absolutely! Let's open those black boxes and bring transparency to AI tools. Count me in to tackle the observability gap!

Weights & Biases1 year ago

🫡

web3MATO 🐦‍🔥1 year ago

Chain abstraction is a game-changer, but adoption is the real test! 🚀 Curious—how does @wandb plan to tackle scalability & cross-chain UX? Looking forward to seeing this evolve!

Dylan Heagy1 year ago

What do you think is the biggest barrier to adoption for this?

Weights & Biases1 year ago

Hey Dylan, great question! We've outlined a few issues in the MCP RFC we posted, namely - While this isn't in the MCP spec, there isn't a standard way for clients and servers to show the developer a combined trace tree - For servers, authentication into Otel backends will be an issue, so we propose a way to have the Client receive and organize all the traces - As with every protocol, even if our proposal is accepted, adoption into the various SDKs (Python, TypeScript, C# etc) will take time But we are committed to make sure MCP will be fully observable!

Related Videos

Today we are announcing Box Agent Security and Governance. AI agents are reading files, moving content, and triggering actions across your most sensitive data at machine speed. Most security tools were not designed for this. Box closes the gap at the content layer: · Prompt injection detection before it reaches the model · Agent guardrails on what agents can and cannot do · Classification-based access policies extending Box Shield to AI · Audit trails for every agent session No additional software. No per-vendor configuration.

Today we are announcing Box Agent Security and Governance. AI agents are reading files, moving content, and triggering actions across your most sensitive data at machine speed. Most security tools were not designed for this. Box closes the gap at the content layer: · Prompt injection detection before it reaches the model · Agent guardrails on what agents can and cannot do · Classification-based access policies extending Box Shield to AI · Audit trails for every agent session No additional software. No per-vendor configuration.

Box

749,502 views • 1 month ago

Your data is only as valuable as what you build on top of it. We now integrate with Databricks to let enterprise teams vibe code living applications and deploy them directly into Databricks Apps: with governance, security, and observability built in. 👷🏼‍♂️ More builders. 🛠️ Better tools. 🎮 No compromises on control.

Your data is only as valuable as what you build on top of it. We now integrate with Databricks to let enterprise teams vibe code living applications and deploy them directly into Databricks Apps: with governance, security, and observability built in. 👷🏼‍♂️ More builders. 🛠️ Better tools. 🎮 No compromises on control.

Replit ⠕

42,008 views • 7 months ago

Just tried SecureIntent and honestly, this is one of those tools you don’t realize you need until you see what it catches. It adds a security layer between your browser and AI tools, helping detect sensitive data like API keys, tokens, and credentials before you accidentally paste them. And the Pro Lifetime offer makes it even more interesting no subscription, no renewals. Worth checking out 👇

Just tried SecureIntent and honestly, this is one of those tools you don’t realize you need until you see what it catches. It adds a security layer between your browser and AI tools, helping detect sensitive data like API keys, tokens, and credentials before you accidentally paste them. And the Pro Lifetime offer makes it even more interesting no subscription, no renewals. Worth checking out 👇

Sheral Tech

21,375 views • 10 days ago

Building web apps? You likely love Playwright. 💜 But what about native Desktop/Mobile apps? ⁉️ Uno Platform brings the same automation. 💪 So, Playwright for .NET apps on web/desktop/mobile. Power through MCP Servers. 🎉 ☑️ Agentic workflows initialized & grounded in Docs ☑️ MCP Tools for app interactivity ☑️ Confidence with validated app runtime behaviors No more guessing. Automate app testing. AI Agents work for you with the right tools.

Building web apps? You likely love Playwright. 💜 But what about native Desktop/Mobile apps? ⁉️ Uno Platform brings the same automation. 💪 So, Playwright for .NET apps on web/desktop/mobile. Power through MCP Servers. 🎉 ☑️ Agentic workflows initialized & grounded in Docs ☑️ MCP Tools for app interactivity ☑️ Confidence with validated app runtime behaviors No more guessing. Automate app testing. AI Agents work for you with the right tools.

Sam Basu

17,298 views • 4 months ago

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!

matt palmer

40,657 views • 1 month ago

This is what happens when the right people are in the right room micaiah joined us to find developers, feel their pain points, and build better tools > His co-founder ludo took the Advanced SVM cohort. discovered LiteSVM. saw the gap. > Together they built Surfpool, now it's one of the main tools devs use on Solana we just build the room. they ship what matters. So proud of these two chads micaiah ludo checkout Micaiah sharing his #Turbin3 journey 👇

This is what happens when the right people are in the right room micaiah joined us to find developers, feel their pain points, and build better tools > His co-founder ludo took the Advanced SVM cohort. discovered LiteSVM. saw the gap. > Together they built Surfpool, now it's one of the main tools devs use on Solana we just build the room. they ship what matters. So proud of these two chads micaiah ludo checkout Micaiah sharing his #Turbin3 journey 👇

Turbin3

12,097 views • 4 months ago

🔮 MCP INTEGRATION NOW LIVE ON OPENSERV This is bigger than most realize. We're not just adding a feature - we're enabling a fundamentally new paradigm for agent infrastructure. Before MCP: agents trapped in walled gardens, limited by what you explicitly feed them. After MCP: agents that can access 10K+ tools, interact with your existing systems, and truly operate in your digital world. Think about this: -Every integration used to require custom code -Every data source needed specific formatting -Every agent had to be built for specific tools MCP eliminates all of that. One standard to connect any agent to any tool. This isn't just convenience - it's the unlock that makes agents actually useful in the real world. OpenServ + MCP = AI teams that can genuinely get things done, not just talk about doing them. This is the breakthrough that turns agents from toys into tools.

🔮 MCP INTEGRATION NOW LIVE ON OPENSERV This is bigger than most realize. We're not just adding a feature - we're enabling a fundamentally new paradigm for agent infrastructure. Before MCP: agents trapped in walled gardens, limited by what you explicitly feed them. After MCP: agents that can access 10K+ tools, interact with your existing systems, and truly operate in your digital world. Think about this: -Every integration used to require custom code -Every data source needed specific formatting -Every agent had to be built for specific tools MCP eliminates all of that. One standard to connect any agent to any tool. This isn't just convenience - it's the unlock that makes agents actually useful in the real world. OpenServ + MCP = AI teams that can genuinely get things done, not just talk about doing them. This is the breakthrough that turns agents from toys into tools.

OpenServ

34,665 views • 1 year ago

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 views • 3 months ago

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!

CyrilXBT

14,347 views • 10 days ago

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!

THIS WEBSITE IS INSANE It contains a huge collection of open-source tools in the browser that don't require registration to use. It includes tools in multiple categories: → Design and Graphics → Development → Productivity → Privacy and Security → AI → Education No accounts. No registrations needed to access them. Just open your browser and start using them Save this now!

MIKE

209,955 views • 13 days ago

Tried something new this time 👀 Calling it Wednesday Waffle. No script, just vibes and real talk. Appreciate all the support. ❤️ What should I talk about next?

Tried something new this time 👀 Calling it Wednesday Waffle. No script, just vibes and real talk. Appreciate all the support. ❤️ What should I talk about next?

Yele | Onboard 🌐

23,909 views • 10 months ago

🎵"Just JGGL it" drift team pilot Adam Zalewski stepped into the studio, and what started as a voiceprint session turned into a full track made entirely with his voice. No music background, no training, just JGGL doing what it does. The energy in the room was something else. Even a racing driver can sound like an artist when the tools are right

🎵"Just JGGL it" drift team pilot Adam Zalewski stepped into the studio, and what started as a voiceprint session turned into a full track made entirely with his voice. No music background, no training, just JGGL doing what it does. The energy in the room was something else. Even a racing driver can sound like an artist when the tools are right

JGGL

12,094 views • 3 months ago

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

17,040 views • 1 month ago

stop consuming content about AI tools and go play with one Replit, ChatGPT, claude, just open something and see what happens the people winning right now aren’t “smarter” they’re just WAY less scared of looking dumb while they attempt to figure it out

stop consuming content about AI tools and go play with one Replit, ChatGPT, claude, just open something and see what happens the people winning right now aren’t “smarter” they’re just WAY less scared of looking dumb while they attempt to figure it out

Mika

20,109 views • 6 months ago

Introducing - Agents Most AI tools are a prompt box. You ask for a thing, a thing appears. No idea what happened in between. The Customuse AI agent isn't. You hand it a goal. It builds the actual node graph in front of you, with nodes you can see, rewire, edit. A real creative collaborator. Live Now.

Introducing - Agents Most AI tools are a prompt box. You ask for a thing, a thing appears. No idea what happened in between. The Customuse AI agent isn't. You hand it a goal. It builds the actual node graph in front of you, with nodes you can see, rewire, edit. A real creative collaborator. Live Now.

Customuse

1,098,923 views • 3 months ago

I've been collecting the best dev resources, and workflows for years. tutorials, tools, UI libs… everything that actually helps you ship today I'm putting it all into one place: this is my biggest project so far in the age of AI, tools are everywhere but real builders and real communities matter more than ever one time entry. no subscriptions. early members will shape what this becomes let's build ⚔️

I've been collecting the best dev resources, and workflows for years. tutorials, tools, UI libs… everything that actually helps you ship today I'm putting it all into one place: this is my biggest project so far in the age of AI, tools are everywhere but real builders and real communities matter more than ever one time entry. no subscriptions. early members will shape what this becomes let's build ⚔️

OrcDev

72,280 views • 4 months ago

I've read a hundred "make money with AI" posts. Most are hype. This one is different. The idea: build a bunch of boring little tools. PDF converters, GST calculators, JSON formatters, word counters. Each one ranks for a keyword. Each visitor sees an ad. Do that 1,000 times and you're at $10K/month. No audience. No content grind. No selling. Just tools that quietly rank and compound for years. The best part is it's actually achievable. AI builds the tools now. The only real work is SEO and getting AdSense set up right. That's exactly what I'm going to do next. Building the tools, ranking them, attaching AdSense. If you haven't read this one yet, go read it. And if you're not sure how to set up AdSense, I attached a video below.

I've read a hundred "make money with AI" posts. Most are hype. This one is different. The idea: build a bunch of boring little tools. PDF converters, GST calculators, JSON formatters, word counters. Each one ranks for a keyword. Each visitor sees an ad. Do that 1,000 times and you're at $10K/month. No audience. No content grind. No selling. Just tools that quietly rank and compound for years. The best part is it's actually achievable. AI builds the tools now. The only real work is SEO and getting AdSense set up right. That's exactly what I'm going to do next. Building the tools, ranking them, attaching AdSense. If you haven't read this one yet, go read it. And if you're not sure how to set up AdSense, I attached a video below.

Ziwen

156,270 views • 3 months ago

Most AI tools feel like a "black box" with no control. You’re locked into their logic. But ProtoPie AI generates the interaction logic with 100% manual override. No locked outputs. No creative ceiling. Use coupon AI2026 at Pro checkout and claim your 1-month of exclusive access!

Most AI tools feel like a "black box" with no control. You’re locked into their logic. But ProtoPie AI generates the interaction logic with 100% manual override. No locked outputs. No creative ceiling. Use coupon AI2026 at Pro checkout and claim your 1-month of exclusive access!

ProtoPie 🥧

10,567,281 views • 5 months ago