71% of MCP packages are MIT — and that tells you almost nothing
We record the license of every package we compile. The distribution is unsurprising and worth stating plainly: 245 of 343 are MIT (71%), 51… We record…
We record the license of every package we compile. The distribution is unsurprising and worth stating plainly: 245 of 343 are MIT (71%), 51… We record…
Directories rank. They rarely tell you what the population looks like. So we measured ours: every npm package we could verify declares an MCP… Directories rank.…
The naive way to build an MCP directory is to query npm for the keyword and publish what comes back. That produces a directory… The naive…
The first time an MCP server fails, it looks like the model is being stupid. It calls a tool, gets nothing back, and apologizes.… The first…
A repository with two files named `config.ts` will send an agent to the wrong one roughly half the time. Nothing about that is mysterious:… A repository…
People budget for conversation tokens and forget the ones that are always there: the system prompt, the tool schemas, and the resource descriptions. They… People budget…
Every week someone installs an MCP server from a list, wires it into their agent, and then spends an afternoon debugging a transport mismatch… Every week…