Комментарии:
Great job Chris in creating and explaining this!
ОтветитьGreat video
ОтветитьExcellent job. I've cloned the repository but I don't find the requirements.txt file, how can I solve it?
ОтветитьI've been wondering, anthropic have many optimizer such as in context rag, prompt caching, and some other more i couldn't remember. I wonder does this MCP server also optimized ready? or we have to optimize them by our self?
ОтветитьInteresting development, Chris.
ОтветитьAmazing Chris! I see your video with Claude Desktop which seems perfect, but kind of blackbox form me. Now you change it to devevoper friendly playground with source code explanation - big thank you !!!
ОтветитьThis is what I expected from MCP, not having it tied to Claude Desktop, good job !
ОтветитьWorks well! Tried with ollama sqlite. An interresting new cli option could be to transform it in "server" mode able to receive / respond to messages coming from api calls so the chat+mcp will be available from remote computers/agents
ОтветитьAmazing work :)
Ответитьhow does this compare to autogen, how can they work together? seems some overlapping but not really... can't quite wrap my head around them for integration
ОтветитьDeepSeek would be the best Alternative to claude
, i think
This is exactly the video i was looking for. AI is crazy, every day news worth seeing
ОтветитьThat's awesome! Would it be possible to connect to other databases (eg. MSSQL) and call up stored procedures specificially, instead of relying on AI to write the SQL?
Ответитьgreat video! can you make a follow up on how to get this integrated into something like Open WebUI?
ОтветитьLegend. Just came across MCP and was hoping someone would build a client as a demo. Thanks.
ОтветитьA wonderful implementation and explanation!
ОтветитьThis would be cool to use as a host with FastMCP for servers
ОтветитьNice
ОтветитьI do understand the olama obsession. Just use Claude, it’s already built and functional
ОтветитьVery cool! 👍
ОтветитьUntil the day bills created by AI
Ответитьworks pretty well however i would mention uv can be installed onto your base system and with your setup it will complain if you use your own venv and its not a good idea to install python packages to your base system just a note for anyone else. btw i used it with llama3.2
Ответитьsubbed
ОтветитьFantastic! Cannot wait to check the source codes!!
ОтветитьThank you for your video.
ОтветитьVery cool. I added the memory mcp and tavily search to the config. Seems like it works, The current setup requires one cli per server, is that correct?
ОтветитьFantastic work here, thanks Chris!
ОтветитьVery nice! Can it handle multiple steps in one shot like Claude Desktop ?
ОтветитьThis is tremendous, Chris! I learned so much....and really enjoy the way you present the information. Thank you!
ОтветитьOllama Need so expensive PC
ОтветитьGreat job Chris, any plans to support multiple servers like Claude Desktop can? I've built an MCP server that can build Powerpoint decks, I can chain with the SQLite mcp server to pull data sources from a database and dynamically build tables and charts in Powerpoint. All in one prompt
ОтветитьExcellent stuff, thank you. Would love to see a video on how to use JSONRpc in other projects.
Ответитьplease integrate it with together api key
Ответитьi wish you do this video step by step.. Because i dont understand anyting
ОтветитьThank you so much for this video! It helped me add MCP tools to my node JS local LLM project.
Ответить