Claude code setup + minor readme (#25)

* add claude-code support for init

* update readme

Author: buixor

.github/workflows/build-mcpb.yml

@@ -22,7 +22,7 @@ jobs:
       - name: Build MCPB package
         run: |
           mkdir -p dist
-          npx --yes @anthropic-ai/mcpb pack
+          npx --yes @anthropic-ai/mcpb@v1.1.1 pack
 
       - name: Upload package artifact
         uses: actions/upload-artifact@v4

README.md

@@ -46,12 +46,19 @@
 
 ## Installation
 
-### Quick MCP client setup
+### Using `.mcpb` package
 
-- Configure supported clients automatically with `uvx --from crowdsec-local-mcp init <client>`, where `<client>` is one of `claude-desktop`, `chatgpt`, `vscode`, or `stdio`:
+If you're using `claude desktop`, you can configure the MCP directly by double-clicking the `.mcpb` file that accompanies the release.
+
+> [!IMPORTANT]
+> On MacOS, configure `uv` path in the extension settings if `uv` isn't installed in the standard path. 
+
+### Using `uvx`
+
+- Configure supported clients automatically with `uvx --from crowdsec-local-mcp init <client>`, where `<client>` is one of `claude-desktop`, `claude-code`, `chatgpt`, `vscode`, or `stdio`:
 
 ```bash
-uvx --from crowdsec-local-mcp init claude-desktop
+uvx --from crowdsec-local-mcp init --dry-run claude-code
 ```
 
 Run `uvx --from crowdsec-local-mcp init --help` to see all flags and supported targets.
@@ -60,7 +67,8 @@ Run `uvx --from crowdsec-local-mcp init --help` to see all flags and supported t
 
 The `init` helper writes the CrowdSec MCP server definition into the client’s JSON configuration:
 
-- `claude-desktop` → `claude_desktop_config.json`
+- `claude-desktop` → `claude_desktop_config.json` in the Claude Desktop settings directory
+- `claude-code` → invoke `claude mcp` command with needed args
 - `chatgpt` → `config.json` in the ChatGPT Desktop settings directory
 - `vscode` → `mcp.json` for VS Code (stable and insiders are both detected)
 
@@ -72,6 +80,10 @@ By default the CLI launches the server with `uvx --from crowdsec-local-mcp crowd
 
 `stdio` does not modify any files. Instead, `init stdio` prints a ready-to-paste JSON snippet that you can drop into any stdio-compatible MCP client configuration. This is useful when you want to manually wire the server into tools that do not have built-in automation support yet.
 
+## Troubleshooting
+
+If you just installed the mcp extension via `.mcpb` and `uv` or `uvx` isn't in the standard path, check the extension settings to configure `uv` path.
+
 ## Logging
 
 - The MCP server writes its log file to your operating system's temporary directory. On Linux/macOS this is typically `/tmp/crowdsec-mcp.log`; on Windows it resolves via `%TEMP%\crowdsec-mcp.log`.

manifest.json

@@ -106,9 +106,6 @@
   ],
   "tools_generated": true,
   "prompts_generated": true,
-  "compatibility": {
-    "uv": ">=0.5.0"
-  },
   "keywords": [
     "crowdsec",
     "foss",

src/crowdsec_local_mcp/_version.py

@@ -1 +1 @@
-__version__ = "0.0.2.post1.dev24"
+__version__ = "0.4.0.post1.dev0"

src/crowdsec_local_mcp/setup_cli.py

@@ -2,15 +2,16 @@
 import json
 import os
 import platform
+import shlex
 import shutil
+import subprocess
 import sys
 from dataclasses import dataclass
 from pathlib import Path
 from collections.abc import Iterable
 
 SERVER_KEY = "crowdsec-local-mcp"
-SERVER_LABEL = "CrowdSec MCP"
-
+SERVER_LABEL = "CrowdSecMCP"
 
 @dataclass
 class CLIArgs:
@@ -42,6 +43,8 @@ def main(argv: Iterable[str] | None = None) -> None:
 
     if args.target == "claude-desktop":
         _configure_claude(args, server_payload)
+    elif args.target == "claude-code":
+        _configure_claude_code(args, server_payload)
     elif args.target == "chatgpt":
         _configure_chatgpt(args, server_payload)
     elif args.target == "vscode":
@@ -55,12 +58,12 @@ def _parse_args(argv: Iterable[str] | None) -> CLIArgs:
         prog="init",
         description=(
             "Initialize CrowdSec MCP integration for supported clients "
-            "(Claude Desktop, ChatGPT Desktop, Visual Studio Code, or stdio)."
+            "(Claude Desktop, Claude Code, ChatGPT Desktop, Visual Studio Code, or stdio)."
         ),
     )
     parser.add_argument(
         "target",
-        choices=("claude-desktop", "chatgpt", "vscode", "stdio"),
+        choices=("claude-desktop", "claude-code", "chatgpt", "vscode", "stdio"),
         help="Client to configure.",
     )
     parser.add_argument(
@@ -139,6 +142,51 @@ def _configure_claude(args: CLIArgs, server_payload: dict[str, object]) -> None:
     )
 
 
+def _configure_claude_code(args: CLIArgs, server_payload: dict[str, object]) -> None:
+    runner_command = server_payload["command"]
+    if not isinstance(runner_command, str):
+        raise TypeError("Server payload 'command' must be a string.")
+    runner_args = server_payload.get("args", [])
+    if not isinstance(runner_args, list):
+        raise TypeError("Server payload 'args' must be a list.")
+
+    claude_invocation = [
+        "claude",
+        "mcp",
+        "add",
+        "--transport",
+        "stdio",
+        "--scope",
+        "user",
+        SERVER_LABEL,
+        "--",
+        runner_command,
+        *runner_args,
+    ]
+    quoted_command = " ".join(shlex.quote(part) for part in claude_invocation)
+
+    if args.dry_run:
+        print(
+            "Run the following command to register CrowdSec MCP with Claude Code:\n"
+            f"{quoted_command}"
+        )
+        return
+
+    if shutil.which("claude") is None:
+        raise FileNotFoundError(
+            "The 'claude' CLI is not available on PATH. Install Claude Code CLI and "
+            f"run:\n{quoted_command}"
+        )
+
+    result = subprocess.run(claude_invocation, check=False)
+    if result.returncode != 0:
+        raise RuntimeError(
+            f"'claude mcp add' failed with exit code {result.returncode}. "
+            f"Run manually:\n{quoted_command}"
+        )
+    print("Registered CrowdSec MCP with Claude Code CLI.")
+
+
 def _configure_chatgpt(args: CLIArgs, server_payload: dict[str, object]) -> None:
     config_path = _resolve_path(args.config_path, _chatgpt_candidates())
     _write_mcp_config(