I counted the MCP servers on my laptop: 43, and 9 are in no config file An engineer's audit of a single laptop found 43 MCP server entries reachable by 13 AI applications, of which 34 were named in a settings file and 9 were not, according to the first-person count published in the article. The 9 unlisted entries came from plugins (7), a VS Code extension that registers servers in code at runtime (1), and a desktop AI app using its own non-MCP protocol (1); 5 of the 9 had nothing that could stand in front of them and 3 held a credential in plain text. The author argues security teams should inventory what an AI coding agent can reach rather than which applications engineers use, noting the 43 entries resolve to 26 distinct server names and that one laptop is not a survey. 43 MCP servers on one laptop. 9 are in no settings file. Security teams ask engineers which AI tools they use. The answer they get is a list of applications. That list is the wrong unit. An AI coding agent is not dangerous because of its name. It is dangerous because of what it can reach: the servers it connects to, the commands it may run, the sign-ins it borrows. So I stopped counting applications and counted reach, on my own laptop. The count | What | Number | |---|---| | AI applications that can act for me | 13 | | MCP server entries those applications can call | 43 | | Entries named in a settings file | 34 | | Entries no settings file names | 9 | | Of those 9, entries with nothing that can stand in front | 5 | | Entries with a credential in plain text | 3 | 43 counts entries, not distinct servers. There are 26 distinct names. The same server declared for two applications counts twice, because each application reaches it on its own, with its own sign-in. I build agentic systems every day, so my laptop is heavier than most. One laptop is also not a survey. But the shape of the result is what matters, and I expect it to repeat on any engineer's machine. Four places a server can come from An inventory script reads the first place. The other three are where the 9 came from. 1. A settings file: 34 entries Each agent keeps its own file, in its own format. | Agent | Where it names its servers | |---|---| | Claude Code | ~/.claude.json , per user and per project, plus .mcp.json in a repository | | Codex | ~/.codex/config.toml , one mcp servers.