Accelerator Interview Scoring

Accelerator Interview Scoring MCP Connector for Claude

A+

Analyze interview scoring consistency and identify calibration needs to ensure fair candidate evaluations.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner

This MCP server provides tools to evaluate the quality and uniformity of candidate evaluations. It helps organizations ensure that candidate scores reflect merit rather than interviewer subjectivity. Use get_scoring_consistency to measure agreement among interviewers, evaluate_calibration_needs to identify when standards need alignment, and calculate_score_adjustments to mitigate interviewer bias through mathematical corrections.

interviewingscoringbias-correctionreliabilitycalibration

3 tools expose this connector's capabilities to your AI agent.

calculate_score_adjustments

Answers "How should we adjust individual scores to compensate for interviewer bias?"

evaluate_calibration_needs

Answers "Which interviewers or candidates require a calibration session to align standards?"

get_scoring_consistency

Answers "How much do our interviewers agree on candidate evaluations?"

See how to talk to your AI agent using Accelerator Interview Scoring.

How much do our interviewers agree on these scores: [8, 7, 9, 8] with a reliability of 0.8?

The scoring consistency is high, indicating strong agreement among the interviewers.

Do we need a calibration session? The variance is 0.5, training level is 0.7, and history is [].

No, current variance is within acceptable limits for the current training level.

Adjust these scores [7, 9] for a bias coefficient of -0.2 and training effect of 0.1.

The adjusted scores are [7.2, 8.8].

It uses `calculate_score_adjustments` to apply mathematical corrections to scores from lenient or harsh interviewers, ensuring a more neutral evaluation.

Related Connectors