You have 50 resumes to screen. Your AI assistant can reason about candidates — but it cannot open PDFs, extract structured data, or track pipeline stages. This toolkit bridges that gap.
Give your AI assistant 24 tools covering the entire hiring workflow:
Parse PDFs, DOCX, TXT, Markdown, and URLs into structured JSON
Extract skills, experience, keywords, and entities algorithmically
Score and rank candidates against job descriptions
Run a full ATS: jobs, candidates, interviews, offers, notes, and analytics
23 of 24 tools are 100% algorithmic — no LLM calls, no API keys required. The AI calls tools, interprets the results, and delivers analysis. You just ask questions.
All 24 MCP Tools
All tools return structured JSON with next_steps hints so the AI knows what to call next.
Resume Parsing & Ingestion
Tool What it does AI?
parse_resume Parse PDF / DOCX / TXT / MD / URL → raw text + contacts, keywords, section map No
batch_parse_resumes Parse up to 20 files in one call, full pipeline on each No
inspect_pipeline Run the 5-stage analysis pipeline → confidence scores, entity counts, data quality report No
Text Analysis & NLP
Tool What it does AI?
extract_keywords TF-IDF keyword + bigram extraction with NER entity classification No
detect_patterns Find date ranges, dollar/percent metrics, team sizes, section boundaries, career trajectory signals No
classify_entities NER with 12 entity types (PERSON, ORG, SKILL, JOB_TITLE, LOCATION, DATE, …) + context disambiguation No
extract_skills_structured Map extracted skills into 13 categories with proficiency estimation (beginner → expert) No
extract_experience_structured Parse work history into structured timeline with start/end dates, achievements, and technologies No
analyze_resume_comprehensive Master tool — full pipeline + entities + keywords + skills + experience in one call No
Candidate Matching & Scoring
Tool What it does AI?
compute_similarity Cosine, Jaccard, TF-IDF overlap, and skill-match scores between resume and job description No
assess_candidate Score against up to 8 weighted criteria axes → weighted total + pass / review / reject decision Optional
manage_candidates Rank, filter, compare, and recommend pipeline stage changes across a candidate pool No
Export & Notifications
Tool What it does AI?
export_results Export structured parse results to JSON or CSV No
send_email Send results via SMTP (config passed per call — no server-side secrets stored) No
ATS — Jobs
Tool What it does AI?
ats_manage_jobs Full CRUD for job postings: create, read, update, delete, list, search by title/department/status No
ATS — Candidates & Pipeline
Tool What it does AI?
ats_manage_candidates CRUD + pipeline operations: add, update, move stage, bulk-move, filter by stage/score/tags No
ats_pipeline_analytics Stage distribution, conversion rates, avg time-in-stage, bottleneck detection, drop-off analysis No
ats_dashboard_stats One-call hiring health report: open roles, candidates by stage, interview load, offer acceptance rate No
ats_search Global full-text search across all ATS entities (candidates, jobs, interviews, offers, notes) No
ATS — Interviews
Tool What it does AI?
ats_schedule_interview Create, update, and delete interviews with conflict detection and interviewer availability check No
ats_interview_feedback Submit structured feedback, compute consensus score, summarize feedback across all interviewers No
ATS — Offers & Notes
Tool What it does AI?
ats_manage_offers Full offer lifecycle: draft → pending → approved → sent → accepted / declined / expired No
ats_manage_notes Add, update, search, and delete timestamped candidate notes No
Testing & Seeding
Tool What it does AI?
ats_generate_demo_data Generate a realistic sample ATS dataset (jobs, candidates, interviews, offers) for testing No
assess_candidate optionally calls an LLM when you supply provider + apiKey; it falls back to fully algorithmic scoring otherwise.