CareerProof MCP Server

Check the status of any async task. Returns status (pending/running/completed/failed), progress percentage, and current stage.

Retrieve the full result of a completed async task. Supports analysis, batch_gem, jd_fit_batch, report, custom_eval_inference, custom_eval_batch, and dialogue_assessment result types.

Create a new hiring context (company profile) for organizing candidates and JDs.

List all hiring contexts for the authenticated user.

Update a hiring context's details (name, industry, size, hiring context).

Upload a candidate CV (PDF/DOCX) to a hiring context. CV parsing starts asynchronously.

List all candidates in a hiring context.

Get full candidate detail including parsed CV content and parse status.

Create a job description from text within a hiring context.

List all job descriptions for a hiring context.

Get comprehensive talent analytics dashboard data (candidate stats, analysis coverage, fit score distributions).

Start an async GEM (10-factor competency) analysis on a candidate. Poll with careerproof_task_status, then fetch with atlas_get_analysis.

Retrieve a completed analysis result by analysis ID. Returns scores, competency breakdown, and recommendations.

List all analyses for a candidate with optional type filtering.

Analyze a JD for market competitiveness, clarity, bias detection, salary benchmarking, and skills extraction. Synchronous.

Start a batch GEM analysis across multiple candidates. Poll with atlas_get_batch_gem_status.

Check progress of a batch GEM job.

Get all results from a completed batch GEM job.

Match multiple candidates against a JD. Poll with atlas_get_jd_fit_batch_status.

Check progress of a JD-FIT batch job.

Get JD-FIT results for a context. Returns ranked candidates with fit scores.

Batch evaluate candidates using a custom evaluation model. Poll with atlas_get_custom_eval_batch_status.

Check progress of a custom evaluation batch.

Get results from a completed custom eval batch.

Generate a research report (market_research, competitor_analysis, or talent_landscape). Poll with careerproof_task_status.

Get report status and metadata.

Download a completed report as base64-encoded PDF.

List all generated reports with status and summary.

Assess dialogue/interview transcripts in a session. Poll with careerproof_task_status.

Get assessment results for a dialogue session.

Auto-generate evaluation dimensions for a custom eval model. Poll with careerproof_task_status.

Create a new custom evaluation model for a hiring context.

List all custom evaluation models for the authenticated user.

Get full detail for a custom eval model including dimensions, weights, and rubric status.

Update a custom eval model's metadata (name, description, dimensions, weights).

Delete a custom evaluation model and all its artifacts and rubrics.

Upload a file artifact (CV, JD, template) as base64 to teach the model.

Add a plain text artifact to teach the model (rubric notes, criteria, descriptions).

List all artifacts uploaded to a custom eval model.

AI infers evaluation rubric from artifacts. Sync call, may take 30-60 seconds.

Get the current rubric including dimensions, scoring criteria, and any overrides.

Set rubric overrides to customize AI-inferred rubric (adjust weights, rename dimensions).

Clear all rubric overrides, reverting to AI-inferred rubric.

Full-featured Atlas AI assistant with live tool use (salary benchmarks, talent supply/demand, competitor intel). May take 2-3 min for complex queries.

Lightweight hiring advice — faster and cheaper than atlas_chat, no tool use.

Start async fit match for a single candidate against a JD. Returns task_id and analysis_id.

Enhanced FIT match with knowledge base augmentation for deeper analysis and market context.

Start async fit rank for multiple candidates against a JD. Returns task_id and analysis_id.

Generate interview questions tailored to a candidate's profile. Supports pressure levels.

Generate a follow-up probing question based on a candidate's answer.

Upload a CV file (PDF/DOCX). Parses the document and creates a CV version with structured sections.

List all CV versions for the authenticated user.

Get detailed CV version including structured content, sections, word count, and audience profile.

List all positioning sessions (market analysis through lens selection to targeted edits).

Get full positioning session detail including analysis, lens, opportunities, targeted edits, and PDF URLs.

Step 1/3 — Run market positioning analysis. Returns snapshot, detected lens, recruiter inference, and session_id.

Step 2/3 — Get career pivot opportunities based on a selected narrative lens.

Step 3/3 — Confirm lens and generate targeted CV edits with trade-offs and optional PDF output.

Autonomous full CV review in one call: positioning + lens + edits + optional opportunities. Alternative to the 3-step pipeline.

List all available career-intel report types with descriptions, required/optional inputs, and credit costs. Call before ceevee_generate_report.

Queue async career-intel report generation. Poll with ceevee_get_report every 30s (max 40 polls / 20 min). Report types: Compensation Benchmark, Role Evolution, Offer Comparison, AI Displacement Risk, Pivot Feasibility, Credential ROI, Skill Decay Risk, Rate Card, Career Gap Narrative, Interview Prep, Employer Red Flag, Industry Switch, Relocation Impact, Startup vs Corporate, Learning Path, Board Readiness, Fractional Leadership.

List user's generated reports with pagination and optional status filter.

Get report status and metadata (without PDF). Use to poll after ceevee_generate_report — every 30s, max 40 polls.

Download a completed report as PDF (base64). Only call after ceevee_get_report confirms status='completed'.

CV optimization guidance with context-aware conversations linked to a CV version.

Detailed explanation of a specific edit from a positioning review.