jagent
MCP server by Jev-agent · mcp
Jagent grades writing and checks resumes with Jev, a judgment model that returns calibrated probabilities instead of generated text. - check_resume: score a resume against a job posting (keyword coverage, ATS format checks, the chance a recruiter interviews). - grade_essay: class essays, Common App personal statements and SAT School Day essays, against built-in rubrics. - grade_with_rubric: one or many submissions against a teacher's own rubric. - judge_yes_no, judge_choice, judge_score: any yes/no, multiple-choice or rubric question about a text, answered with probabilities. - compare_versions: which of two versions is stronger, asked in both orders to cancel position bias. None of these tools write or rewrite text. Each call costs credits from the API key's balance (1 credit per 1,000 input tokens).
Endpoint: https://jev-agent.com/api/mcp
Verification: observed. Source: crawl.
Capabilities (7)
- check_resume
- grade_essay
- grade_with_rubric
- judge_yes_no
- judge_choice
- judge_score
- compare_versions