Mcpx-eval

What's Changed
* cleanup: more tests, improve output of multiple results by zshipko in https://github.com/dylibso/mcpx-eval/pull/8


**Full Changelog**: https://github.com/dylibso/mcpx-eval/compare/v0.2.0...v0.2.1

What's Changed
* chore: update to mcp-run client with oauth support by zshipko in https://github.com/dylibso/mcpx-eval/pull/7


**Full Changelog**: https://github.com/dylibso/mcpx-eval/compare/v0.1.4...v0.2.0

What's Changed
* fix: improve separation of judge and test profiles by zshipko in https://github.com/dylibso/mcpx-eval/pull/6


**Full Changelog**: https://github.com/dylibso/mcpx-eval/compare/v0.1.3...v0.1.4

What's Changed
* fix: judge profile by zshipko in https://github.com/dylibso/mcpx-eval/pull/5


**Full Changelog**: https://github.com/dylibso/mcpx-eval/compare/v0.1.2...v0.1.3

What's Changed
* fix: use judge model for judge analysis by zshipko in https://github.com/dylibso/mcpx-eval/pull/3


**Full Changelog**: https://github.com/dylibso/mcpx-eval/compare/v0.1.1...v0.1.2

* System prompt tweaks

**Full Changelog**: https://github.com/dylibso/mcpx-eval/compare/v0.1.0...v0.1.1