wsp servers add

usage: wsp servers add <name> [<thread>] [--on <computer>] --agent <id>
       (--command "<line>" | --url <address> [--header <name>=<VARIABLE>]...)
       [--env <NAME>]... [--project [<name>]]
  writes one MCP server into an agent's own config: a command with its arguments
  and variables, or an address with its headers, each value read off this
  terminal's environment and written into that file on this computer, a
  variable's value kept in the vault as well; on any other the file names a
  variable and the value goes to the vault, an argument or the address naming a
  variable as ${NAME} keeps that name there, and an agent that reads no variable
  there refuses it

  --agent      the agent whose config takes the server, by its catalog id
  --on         the computer to read, by the name wsp computers shows; this
               computer without it, and a thread names its own
  --command    the line the server runs, its program and arguments in one quoted
               value, split as a shell splits it and nothing expanded; or --url
  --env        a variable the server is given, or one the address names as
               ${NAME}, by its name, its value read off the same name in this
               terminal's environment; an argument or the address may name it as
               ${NAME}; repeats
  --url        the server's https address; or --command
  --header     <name>=<VARIABLE>, a header sent to the address with its value
               read off that variable in this terminal's environment; repeats
  --project    put it in a project's file rather than the agent's own: alone
               with a thread, the thread's own project, or the project's name
               with --on
  --json       print the raw protocol values, one JSON object per line, with
               everything else on stderr
  --state      the state file the host serves
  --host       run the line against a host on your account, by the name wsp
               hosts lists it under; WSP_HOST names one for a whole shell