203 karma · joined August 9, 2023
The extension itself is a MCP server which can be connected to by other extension over cross extension messaging. Since the extension is part of the protocol, I'd like for the community to pull from the same important parts of the extension (MCPHub, content script) so they are consistent across extension implementations.
MCP-B is a different approach. Website owners create MCP servers `inside` their websites, and MCP-B clients are either injected by browser extensions or included in the websites JS.
Instead of visual parsing like Playwright, you get standard deterministic function calls.
You can see the blog post for code examples: https://mcp-b.ai/blogs
The examples focus mostly on extensions injecting clients at website load time, but you can ship a client with your server javascript. That being said, if the client and server live in the the same script I recommend just using the InMemoryTransports from the official SDK.
This was an idea I had while trying to build MCP servers internally at Amazon. Today I am open sourcing it. TLDR it's an extension of the Model Context Protocol which allows you to treat your website as an MCP server which can be discovered and called by MCP-B compliant web extensions.
You can read a more detailed and breakdown here (with gifs): https://mcp-b.ai/blogs
A man’s search for meaning is perhaps the best book on a cure for this affliction. I have a hard time taking seriously people who believe their problems are unique
They recently (<2 years ago) arrested basically every criminal in the country and have the highest incarceration rate in the world by far. It’s a bit controversial internationally but the El Salvadorian people love it.
All I can say is visit now while it’s a well kept secret. I’ve never felt safer in a Latin American country. it’s beautiful, cheap and authentic. It feels like a country on the rise. While driving there it felt like everything was under construction (in a good way)
Rapier was brand new when I was making things in R3F 2 years ago. Glad to see how mature it’s gotten!
You’d think with all the funding these companies have they’d make better technical decisions
Basically when we onboard a new client they dump all their audiograms on us as PDFs.
The data needs extraction needs to be perfect because the tables values are used to detect hearing loss over time.
We settled on a pipeline that looks roughly like
PDF -> gpto pre filter phase -> OCR to extract text tables and forms -> things branch out here
We do a direct parse of forms and text through an LLM
Extract audiogram graphs and send them to a foundation convnet
Attempt to parse tables programmatically
-> an audiogram might have 3 separate places where the values are so we pass the results of all three of these routes through Claude sonnet and if they match they get auto approved. If they don’t, they get flagged for manual review.
All in all it’s been a journey but the accuracy is near 100 percent. These tools are incredible
With the right prompt, it produced extremely clean and workable code.
~20 controller files and over 100 route handlers were converted in about 20 minutes and 5 dollars.
The engineering cost of migrating code bases is trending to 0