testivai

npx -y @testivai/mcp@0.5.5
B
82.6/100
8 tools · agent gemini:gemini-flash-latest

Dimensions

Schema Health100.0 ×1
Description Quality (heuristic)100.0 ×1
Security Signals100.0 ×2
Agent Task Success33.3 ×3
Tool-Selection Accuracy100.0 ×1.5
Tool Reliability100.0 ×1
Response Safety (runtime)100.0 ×1
Robustness100.0 ×1

Agent evaluation

3 tasks × 2 repeat(s)  gemini:gemini-flash-latest
TaskPassScoreTools
Fetch the visual testing report using the appropriate tool, then summarize the total number of snapshots evaluated and l2/2100100
First, fetch the test report to discover snapshot names that have visual changes. Then, retrieve the diff images for one0/20100
Obtain the visual testing report to locate a changed snapshot, then request a detailed evidence explanation for that spe0/20100
Excluded (possibly-mutating) tools: get_visual_results, approve_snapshot, approve_all, list_baselines

Findings

Agent Task Success
medium
server: agent failed a task (0/2 passed) — agent did not complete it (agent signal)
First, fetch the test report to discover snapshot names that have visual changes. Then, retrieve the diff images for one — The agent was unable to retrieve diff images because the test report contained no test results or changed snapshot names.
medium
server: agent failed a task (0/2 passed) — agent did not complete it (agent signal)
Obtain the visual testing report to locate a changed snapshot, then request a detailed evidence explanation for that spe — The visual testing report contained no test results, so no changed snapshot could be located or explained.