Great work! I think the failure to append to the resource may be because whatever method (db call?) that Claude Desktop is using to append isn't launched or isn't available from your standalone environment. Claude desktop has a "Local Storage" folder (which I have not used). In this folder there is leveldb folder.
Yeah. Sounds about right. I need to dig in to the code more. From my memory it’s just updating an in memory string ‘memo’. I’m not exactly sure what the point of it is, there is no tool to query it, just write. :/
Okay. Had a long chat with the developer at Anthropic who wrote the SQLite server. There is an asynchronous call from the server that is looking for my response out of band of the agentic workflow. I’m going to work on this and get a fix. I’m also going to work on the other parts of MCP like prompts and sampling. It was s super useful and great chat.
Can you please make a video to deploy and train a sagemaker based keras tensorflow model but on like numerical data not image data say for example classifying weather a person has diabetes or not based on some given feature. I have searched whole youtube but couldnt find a single video on it. All tensorflow videos are only for image data none for numerical data. And great work by the way. I just love your content.
@mikegchambers yes actually I have. And I got a different perspective of performing sklearn based deployment from this video. Problem is I am trying to work on tensorflow deployment model but on numerical data and somehow I have tried everything but during training job my model is running but its not getting saved and i am getting a warning. I am new to ml.I have tried like everything to the best of my knowledge. Even refereed documentation. And tensorflow based model deployment but on numerical data is something I am after.
Thanks for sharing! I'm wondering how to fix this problem: Error occurred: An error occurred (AccessDeniedException) when calling the Converse operation: You don't have access to the model with the specified model ID.
Hey. Thanks for trying out the code. You will need… an AWS account with credentials in your dev environment. You will also need to have enabled access to the LLMs models, through the Bedrock console page, clicking model access near the bottom of the menu on the left. If you have any issues, reach out and I’ll help you get it sorted.
Would you make a version for SSE where the MCP server and client can be on different machines? All examples I've found and in the github repo from MCP project only the stdio version works, SSE implementation in the SDK seems quite unstable and not well documented.
Hey. So that library is not out yet. I was talking to the team at Anthropic today and it seem they want to get a good authentication design working before they do that. However, there is a workaround, which is to make a local stdio server and have it make a connection across the web. But that is a hack of a workaround only. Let’s keep an eye out for updates.
In theory yes. But you’ll need to modify the code quite a bit. Also you need a model that can handle agentic workflows. This might be a little challenging for a quantised smaller model running on most “home” hardware. Please let me know if you make progress.
Hey! Well… it’s a protocol right? So it’s as fast or slow as the implementation. I was please to see that my super basic code implementation is pretty fast for basic DB operations.
Absolutely, go for it! I think I for deploying larger solutions in production we can often benefit from an API hosted model, but yeah, if you have the hardware that would be fun.
Thanks for going deeper into this than just reading the project home page. We need more videos like this where people explore deeper.
Glad you found it interesting. Thanks for the feedback Jim!
Thanks for covering this topic! Great to know how to use mcp outside of Claude desktop so that it can be deployed
Glad you found it useful. I can see me making a bunch more on this.
Great demo. Thanks for sharing
Thanks for watching!
Awesome Mike!
Thanks!!
awesome, super helpful
Awesome. Thanks for comment.
Gotta love a sci fi movie reference!
I refuse to believe that Anthropic didn’t realise this connection!!
Great work! I think the failure to append to the resource may be because whatever method (db call?) that Claude Desktop is using to append isn't launched or isn't available from your standalone environment. Claude desktop has a "Local Storage" folder (which I have not used). In this folder there is leveldb folder.
Yeah. Sounds about right. I need to dig in to the code more. From my memory it’s just updating an in memory string ‘memo’. I’m not exactly sure what the point of it is, there is no tool to query it, just write. :/
Okay. Had a long chat with the developer at Anthropic who wrote the SQLite server. There is an asynchronous call from the server that is looking for my response out of band of the agentic workflow. I’m going to work on this and get a fix. I’m also going to work on the other parts of MCP like prompts and sampling. It was s super useful and great chat.
@@mikegchambers ❤️
good video
The beard is very nice. I will grow a beard of the same style in the future.
Well… okay. Glad you enjoyed the beard. 🧔 😆
Can you please make a video to deploy and train a sagemaker based keras tensorflow model but on like numerical data not image data say for example classifying weather a person has diabetes or not based on some given feature. I have searched whole youtube but couldnt find a single video on it. All tensorflow videos are only for image data none for numerical data. And great work by the way. I just love your content.
Hey. Have you seen this video? ruclips.net/video/C_AtgCm43Nk/видео.htmlsi=R8HTCMR0Ibqq2ck0
@mikegchambers yes actually I have. And I got a different perspective of performing sklearn based deployment from this video. Problem is I am trying to work on tensorflow deployment model but on numerical data and somehow I have tried everything but during training job my model is running but its not getting saved and i am getting a warning. I am new to ml.I have tried like everything to the best of my knowledge. Even refereed documentation. And tensorflow based model deployment but on numerical data is something I am after.
I have a question that I hope you can help answer: Is it possible to apply MCP to the OpenAI API? If so, how can we do it?
At the risk of dating myself... Tron!
Yay! We have a winner! Thanks. I was beginning to think it was too obscure. You win… my respect!
Thanks for sharing!
I'm wondering how to fix this problem:
Error occurred: An error occurred (AccessDeniedException) when calling the Converse operation: You don't have access to the model with the specified model ID.
Hey. Thanks for trying out the code. You will need… an AWS account with credentials in your dev environment. You will also need to have enabled access to the LLMs models, through the Bedrock console page, clicking model access near the bottom of the menu on the left.
If you have any issues, reach out and I’ll help you get it sorted.
@@mikegchambers I think I fixed the problem, thanks a lot!
Would you make a version for SSE where the MCP server and client can be on different machines? All examples I've found and in the github repo from MCP project only the stdio version works, SSE implementation in the SDK seems quite unstable and not well documented.
Hey. So that library is not out yet. I was talking to the team at Anthropic today and it seem they want to get a good authentication design working before they do that.
However, there is a workaround, which is to make a local stdio server and have it make a connection across the web. But that is a hack of a workaround only.
Let’s keep an eye out for updates.
Is this possible to use Ollama instead of Amazon Bedrock?
In theory yes. But you’ll need to modify the code quite a bit. Also you need a model that can handle agentic workflows. This might be a little challenging for a quantised smaller model running on most “home” hardware.
Please let me know if you make progress.
is this fast? what should i consider to use this instead other tools?
Hey! Well… it’s a protocol right? So it’s as fast or slow as the implementation. I was please to see that my super basic code implementation is pretty fast for basic DB operations.
@mikegchambers i see got it, thanks man, noted.
牛逼
Why bedrock? Just use your own local LLMs and pay NOTHING
Absolutely, go for it! I think I for deploying larger solutions in production we can often benefit from an API hosted model, but yeah, if you have the hardware that would be fun.
Is it possible to use llama?
Well, in the video I show it working with Llama 3.2, so yes, no problems.
@@mikegchambers thanks😃