Get Experiment Results
Get experiment status, per-variant stats, SPRT decision, and winner assessment with confidence and lift percentage. Returns insufficient_data when control has fewer than 5 samples. When a winner is detected, returns lift and confidence. Pure DB operation.
MCP tool name: get_experiment_results
Use Cases
- Check if your A/B test has reached statistical significance
- View per-variant acceptance or reply rates
- Get the confidence level and lift percentage for the winning variant
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
| experiment_id | string | required | UUID returned by launch_experiment |
Example
Prompt
Check the results of my connection note A/B test
Response
{
"status": "completed",
"winner": { "variant_index": 0, "lift": 23.5, "confidence": 0.95 },
"variants": [
{ "name": "A", "sent": 150, "accepted": 45, "rate": 0.30 },
{ "name": "B", "sent": 148, "accepted": 36, "rate": 0.24 }
]
}Permission Scopes
This tool is available in the following permission scopes:
Related Tools
Launch Experiment
Run SPRT-based A/B tests on campaign message variants to find the highest-performing copy via MCP.
Promote Experiment Winner
Apply the winning variant to your campaign so all future sends use the best-performing copy via MCP.
Get Variant Stats
View per-variant performance metrics for a campaign: sent, replied, accepted, rates per step via MCP.
The complete LinkedIn API. Ready when you are.
Connect your first LinkedIn profile in under 5 minutes. All 160 tools. Safe limits, warm-up, and full permission control built in.