error trying to register a new Toolgroup suing the CLI

[rafaeltuelho]

System Info

PyTorch version: 2.6.0
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: macOS 14.7.4 (arm64)
GCC version: Could not collect
Clang version: 16.0.0 (clang-1600.0.26.6)
CMake version: Could not collect
Libc version: N/A

Python version: 3.11.10 (main, Sep 12 2024, 10:17:23) [Clang 15.0.0 (clang-1500.3.9.4)] (64-bit runtime)
Python platform: macOS-14.7.4-arm64-arm-64bit
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Apple M2 Pro

Versions of relevant libraries:
[pip3] numpy==2.2.4
[pip3] torch==2.6.0
[conda] Could not collect

Information

• The official example scripts
• My own modified scripts

🐛 Describe the bug

I'm getting the following error when registering a new Toolgroup through the CLI.

llama-stack-client toolgroups register --provider-id 'brave-search' --provider-toolgroup-id 'builtin::websearch' --args '{"max_results": 5}' --mcp-config {} builtin::brave-websearch

Error logs

╭────────────────────────────────────────────────────────────────────────────────────────╮
│ Failed to register toolgroup                                                           │
│                                                                                        │
│ Error Type: TypeError                                                                  │
│ Details: ToolgroupsResource.register() got an unexpected keyword argument 'mcp_config' │
╰────────────────────────────────────────────────────────────────────────────────────────

Expected behavior

A new tool has been registered.