back
4 comments
> "Claude now lists over 950 MCP servers in the connectors directory, used by millions of people every day. This year we shipped support for new protocol extensions alongside features that make MCP easier to build on and deploy"

Where are all these MCP servers? I feel like if I explore the directory, I see the same subset over and over.

Separately, would love to see more love from Anthropic for MCPB. I think this is an exciting and underutilized variation and have been enjoying building MCPB servers.

I think it is now possible to do one curl to call an MCP tool, instead of three previously.

I tried MCP before but the models still needed a lot of hand-holding to be able to use the MCP tools effectively, and I found that just giving them REST endpoints with good examples and descriptions in the OpenAPI/Swagger docs seems to be a better approach. They can explore the REST endpoints easily with curl to get a hang of them.

You may be able to reduce context usage by having one tool that can leverage multiple API endpoints behind the scenes. This abstraction layer is one of the benefits of MCP.
I could do the same with REST where I create an LLMs' BFF that does all of the aggregations for me so that only the data the LLMs need are returned ;) We already do that for mobile app clients, so LLMs are just another type of clients IMO.

Another approach is to let the LLM explore the MCP on its own but then have it write a simple CLI program which aggregates MCP calls for common workflows so that we don't have to instruct it again and again with Markdown files of how to chain the calls together which it would get right about 80% or less of the time.