Uh oh!
There was an error while loading. Please reload this page.
Benchmark Kernel MCP with ClawBench through Harbor - #162
Conversation
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
The smoke task duplicated what the ClawBench arm already proves. Drop its task definition, runner, verifier, fixtures, and MCP config, and drop stale ignore entries nothing writes. Document only the ClawBench flow.
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Want higher recall? High effort reviews run extra passes and find more bugs. A team admin can switch effort levels in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 9e91f52. Configure here.
Uh oh!
There was an error while loading. Please reload this page.

Summary
KERNEL_MCP_ENABLED_TOOLSETSso self-hosted deployments can positively select tool families; the benchmark exposes onlyget_connection_contextandexecute_playwright_codeexecute_playwright_codeto return a relevant accessibility snapshot or compact page state after every actionkernel-mcp-serverfrom the current Git SHA, run it locally inside the Harbor/Hypeman task, and record that source identity in the verifier manifestValidation
bun test— 249 passedpython3 -m unittest benchmarks/harbor/clawbench/test_control.py— 6 passed