Standardization Protocol for AI agents. Enables them to act, inter-connect, process, parse, invoke functions. In other words to Crawl, Browse, Search, click, etc.
MCP re-uses well known client-server architecture using JSON-RPC.
Apps use MCP Clients -> MCP Servers (abstracts the service)
Kind of API++ for an AI world!
Inspired by Open Source Software (OSS), yet not fully open...
With Open Weight (OW) typically the final model weights (& the fully trained model) are made available under a liberal free to reuse, modify, distribute, non-discriminating, etc licence. This helps for anyone wanting to start with the fully trained Open Weight model & apply them, fine-tune, modify weights (LoRA, RAG, etc) for custom use-cases. To that extent, OW has a share & reuse philosophy.
On the other hand, wrt training data, data sources, detailed architecture, optimizations details, and so on OW diverges from OSS by not making it compulsory to share any of these. So these remain closed source with the original devs, with a bunch of pros & cons. Copyright material, IP protection, commercial gains, etc are some stated advantages for the original devs/ org. But lack of visibility to the wider community, white box evaluation of model internals, biases, checks & balances are among the downsides of not allowing a full peek into the model.
Anyway, that's the present, a time of great flux. As models stabilize over time OW may tend towards OSS...
References
A book by Damien Benveniste of AIEdge. Though a work in progress, chapters 2 - 4 available for preview are fantastic.
Look forward to a paperback edition, which I certainly hope to own...
Mozilla pedigree, AI focus, Open-source, Dev oriented.
Blueprint Hub: Mozilla.ai's Hub of open-source templtaized customizable AI solutions for developers.
Lumigator: Platform for model evaluation and selection. Consists a Python FastAPI backend for AI lifecycle management & capturing workflow data useful for evaluation.
