❯ cargo install --git https://github.com/andrewgazelka/nushell --branch feat/mcp-http-transport --features mcp --root . nu
    Updating git repository `https://github.com/andrewgazelka/nushell`
  Installing nu v0.110.1 (https://github.com/andrewgazelka/nushell?branch=feat%2Fmcp-http-transport#ad4d95ec)
...
   Installed package `nu v0.110.1 (https://github.com/andrewgazelka/nushell?branch=feat%2Fmcp-http-transport#ad4d95ec)` (executable `nu.exe`)
warning: be sure to add `C:\Users\ofek\Desktop\bin` to your PATH to be able to run the installed binaries
❯ let id = (job spawn { ^.\bin\nu --mcp --mcp-transport http }); job spawn { sleep 5sec; job kill $id } | ignore
❯ mcp-inspector --cli --transport http http://localhost:8080/mcp/ --method tools/list
{
  "tools": [
    {
      "name": "command_help",
      "description": "Get help for a specific Nushell command. This will only work on commands that are native to nushell. To find out if a command is native to nushell you can use the find_command tool.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "name": {
            "description": "The name of the command",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "title": "CommandNameRequest"
      }
    },
    {
      "name": "list_commands",
      "description": "List available Nushell native commands.\nBy default all available commands will be returned. To find a specific command by searching command names, descriptions and search terms, use the find parameter.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "find": {
            "description": "string to find in command names, descriptions, and search term",
            "type": "string",
            "nullable": true
          }
        },
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "title": "ListCommandsRequest"
      }
    },
    {
      "name": "evaluate",
      "description": "Execute a command in the nushell.\nThis will return the output and error concatenated into a single string, as\nyou would see from running on the command line. There will also be an indication\nof if the command succeeded or failed.\n\nAvoid commands that produce a large amount of output, and consider piping those outputs to files.\nIf you need to run a long lived command, background it - e.g. `job spawn { uvicorn main:app }` so that\nthis tool does not run indefinitely.\n\nCommand Equivalents to Bash:\n\n| Bash Command | Nushell Command | Description |\n|--------------|-----------------|-------------|\n| `mkdir -p <path>` | `mkdir <path>` | Creates the given path, creating parents as necessary |\n| `> <path>`  | `o> <path>` | Save command output to a file |\n| `>> <path>` | `o>> <path>` | Append command output to a file |\n| `> /dev/null` | `ignore` | Discard command output |\n| `> /dev/null 2>&1` | `o+e>\\| ignore` | Discard command output, including stderr |\n| `command 2>&1` | `command o+e>\\| ...` | Redirect stderr to stdout (use `o+e>` or `out+err>`) |\n| `cmd1 \\| tee log.txt \\| cmd2` | `cmd1 \\| tee { save log.txt } \\| cmd2` | Tee command output to a log file |\n| `command \\| head -5` | `command \\| first 5` | Limit the output to the first 5 rows of an internal command (see also last and skip) |\n| `cat <path>` | `open --raw <path>` | Display the contents of the given file |\n| `cat <(<command1>) <(<command2>)` | `[(command1), (command2)] \\| str join` | Concatenate the outputs of command1 and command2 |\n| `cat <path> <(<command>)` | `[(open --raw <path>), (command)] \\| str join` | Concatenate the contents of the given file and output of command |\n| `for f in *.md; do echo $f; done` | `ls *.md \\| each { $in.name }` | Iterate over a list and return results |\n| `for i in $(seq 1 10); do echo $i; done` | `for i in 1..10 { print $i }` | Iterate over a list and run a command on results |\n| `cp <source> <dest>` | `cp <source> <dest>` | Copy file to new location |\n| `rm -rf <path>` | `rm -r <path>` | Recursively removes the given path |\n| `date -d <date>` | `\"<date>\" \\| into datetime -f <format>` | Parse a date (format documentation) |\n| `sed` | `str replace` | Find and replace a pattern in a string |\n| `grep <pattern>` | `where $it =~ <substring>` or `find <substring>` | Filter strings that contain the substring |\n| `command1 && command2` | `command1; command2` | Run a command, and if it's successful run a second |\n| `stat $(which git)` | `stat ...(which git).path` | Use command output as argument for other command |\n| `echo /tmp/$RANDOM` | `$\"/tmp/(random int)\"` | Use command output in a string |\n| `cargo b --jobs=$(nproc)` | `cargo b $\"--jobs=(sys cpu \\| length)\"` | Use command output in an option |\n| `echo $PATH` | `$env.PATH (Non-Windows) or $env.Path (Windows)` | See the current path |\n| `echo $?` | `$env.LAST_EXIT_CODE` | See the exit status of the last executed command |\n| `export` | `$env` | List the current environment variables |\n| `FOO=BAR ./bin` | `FOO=BAR ./bin` | Update environment for a command |\n| `echo $FOO` | `$env.FOO` | Use environment variables |\n| `echo ${FOO:-fallback}` | `$env.FOO? \\| default \"ABC\"` | Use a fallback in place of an unset variable |\n| `type FOO` | `which FOO` | Display information about a command (builtin, alias, or executable) |\n| `\\` | `( <command> )` | A command can span multiple lines when wrapped with ( and ) |\n\nIf the polars commands are available, prefer it for working with parquet, jsonl, ndjson, csv files, and avro files.\nIt is much more efficient than the other Nushell commands or other non-nushell commands.\nIt exposes much of the functionality of the polars dataframe library. Start the pipeline with `plugin use polars`\n\nAn example of converting a nushell table output to a polars dataframe:\n```nu\nps | polars into-df | polars collect\n```\n\nAn example of converting a polars dataframe back to a nushell table in order to run other nushell commands:\n```nu\npolars open file.parquet | polars into-nu\n```\n\nAn example of opening a parquet file, selecting columns, and saving to a new parquet file:\n```nu\npolars open file.parquet | polars select name status | polars save file2\n```\n\n**Important**: The `glob` command should be used exclusively when you need to locate a file or a code reference,\nother solutions may produce too large output because of hidden files! For example *do not* use `find` or `ls -r`.\nUse command_help tool to learn more about the `glob` command.\n\n**Important**: Variables and environment changes persist across tool calls (REPL-style).\nYou can set a variable in one call and access it in subsequent calls:\n- `let x = 42` in one call, then `$x` in the next call returns 42\n- `$env.MY_VAR = \"hello\"` persists for later calls\n\nHowever, external processes run in their own environment. Use absolute paths when possible.\n",
      "inputSchema": {
        "type": "object",
        "properties": {
          "input": {
            "description": "The Nushell source code to evaluate",
            "type": "string"
          }
        },
        "required": [
          "input"
        ],
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "title": "NuSourceRequest"
      }
    }
  ]
}