Skip to content

Liquescent-Development/mcprobe

View on GitHub ↗Related repositories →

Probe and test MCP servers with configurable Agent vs Agent conversations

active 2026-01-162026-01-27 (UTC)

Complete coverage26,646 / 26,646 hourly files (100%) · 2 absent upstream2023-08-152026-08-29 (UTC)
Events
107
Pushes
31
Pull requests
28
Issues
18
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 12 days from 2026-01-16 to 2026-01-27. Pushes: 31 total, peak 7 in a day. Pull requests: 28 total, peak 5 in a day. Issues: 18 total, peak 4 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
richardkiene7731280

Recent activity

Latest issues, pull requests and releases

  • Issue#64richardkiene2026-01-27 16:06
    Support skipping scenarios via YAML configuration
  • Pull request#65richardkiene2026-01-27 16:05
  • Pull request#65richardkiene2026-01-27 16:05
  • Issue#64richardkiene2026-01-27 15:17
    Support skipping scenarios via YAML configuration
  • Pull request#63richardkiene2026-01-27 15:12
  • Pull request#62richardkiene2026-01-25 18:16
  • Pull request#57richardkiene2026-01-23 22:44
  • Issue#56richardkiene2026-01-23 22:43
    MCP server reports wrong agent model for ADK agents
  • Pull request#55richardkiene2026-01-23 22:14
  • Pull request#55richardkiene2026-01-23 21:54
  • Pull request#53richardkiene2026-01-23 21:15
  • Issue#52richardkiene2026-01-23 20:35
    Add customizable prompts and per-scenario LLM config overrides
  • Issue#44richardkiene2026-01-22 19:11
    Judge receives truncated tool results causing incorrect evaluations
  • Pull request#45richardkiene2026-01-22 19:11
  • Pull request#45richardkiene2026-01-22 18:05
  • Pull request#43richardkiene2026-01-22 17:50
  • Issue#40richardkiene2026-01-22 03:39
    Judge uses paraphrased criteria instead of exact text
  • Issue#39richardkiene2026-01-22 03:17
    Create standalone binaries for distribution
  • Pull request#34richardkiene2026-01-21 03:16
  • Issue#31richardkiene2026-01-21 01:56
    Suppress noisy third-party warnings in pytest output
  • Pull request#32richardkiene2026-01-21 01:56
  • Pull request#32richardkiene2026-01-21 01:56
  • Pull request#30richardkiene2026-01-20 22:57
  • Issue#29richardkiene2026-01-20 21:40
    Synthetic user slips into assistant behavior with smaller models
  • Issue#24richardkiene2026-01-20 20:56
    Track system prompt and MCP tool descriptions in test results

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.