aws / aws/amazon-q-developer-cli

Subagent with K8s MCP server hangs after upgrading kiro

Open
#3,712 1 comment 1 reaction 0 assignees View on GitHub
Dominant language
Rust
Stars
2k
Forks
439
PR merge metrics
No merged PRs in 30d

Description

### Checks

- [x] I have run `q doctor` in the affected terminal session
- [x] I have searched [github.com/aws/amazon-q-developer-cli/issues](https://github.com/aws/amazon-q-developer-cli/issues?q=) and there are no duplicates of my issue
- [x] I have run `q restart` and replicated the issue again

### Operating system

macOS 26.3.0

### Expected behaviour

Subagents configured with K8s MCP tooling should function correctly after upgrading Kiro-CLI to 1.29.1, just as they did previously.
The K8s-powered agent should work both as a subagent and when invoked directly.

### Actual behaviour

After upgrading to 1.29.1, subagents using the K8s MCP tooling hang with no response.
However, when the K8s-powered agent is invoked directly (`kiro-cli --agent k8s`), it works as expected.

### Steps to reproduce

1. Configure a subagent with [K8s MCP tooling](https://github.com/containers/kubernetes-mcp-server/releases/tag/v0.0.60).
2. Upgrade Kiro-CLI to version 1.29.1.
3. Invoke the K8s-powered subagent.
4. Observe that the subagent hangs with no response.

### Environment

```yaml

[q-details]
version = "1.29.1"
hash = "b38a4a5326a279f54908508508053d716c45afcf"
date = "2026-04-03T05:55:40.77818Z (5h ago)"
variant = "full"

[system-info]
os = "macOS 26.3.0 (25D125)"
chip = "Apple M3 Pro"
total-cores = 12
memory = "18.00 GB"

[environment]
cwd = "/Volumes/Work/projects/test"
cli-path = "/Volumes/Work/projects/test"
os = "Mac"
shell-path = "/bin/zsh"
shell-version = "5.9"
terminal = "iTerm 2"
install-method = "unknown"
```

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.