A
licenseA
qualityB
maintenanceEnables LLM clients to analyse job postings, tailor resumes from an evidence-labelled profile, validate every claim against that profile, and track applications, all through deterministic MCP tools.
7
Apache 2.0
CareerProof MCP
Server Details
CareerProof MCP gives AI agents direct access to a professional-grade career and workforce intelligence platform. Two namespaces: atlas_* for HR/TA teams (candidate evaluation, batch shortlisting, competency scoring, interview generation, JD analysis, custom eval frameworks, research reports) and ceevee_* for professionals (CV optimization, career positioning, salary intelligence, market reports). Backed by RAG knowledge from 50+ premium research sources (McKinsey, BCG, HBR, Gartner, WEF)
Ownership verified
- Status
- Healthy
- Uptime
- 95.7% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
B3.1/5.0
Scored across 78 tools
Disambiguation3/5
Descriptions are unusually detailed and explicitly cross-reference siblings (e.g. 'prefer careerproof_wait'), which rescues many pairs. However the set has real overlap: four near-identical fit-matching tools (start_fit_match, start_fit_rank, fit_match_enhanced, start_jd_fit_batch), three chat tools (atlas_chat, atlas_advisor_chat, ceevee_chat), three CV-ingestion paths, and a parallel polling surface (careerproof_task_status vs four per-batch status tools plus careerproof_task_result). An agent must reason carefully to pick the right one, especially across the atlas_ vs ceevee_ product split.
Naming Consistency4/5
Names are uniformly snake_case with a verb_noun structure and clear product prefixes (atlas_, ceevee_, careerproof_), so the family of any tool is obvious at a glance. Minor deviations exist (atlas_fit_match_enhanced puts the qualifier last, atlas_get_analytics/atlas_get_upload_link drop the resource noun), but nothing that breaks predictability.
Tool Count1/5
78 tools is far past what an agent can hold in working context, and the surface spans three product lines (Atlas recruiting, CeeVee CV positioning, shared task plumbing). Many tools exist only as a status/result pair for a background job, inflating the count with near-duplicates rather than distinct capabilities.
Completeness4/5
Coverage is broad and lifecycle-aware: contexts, candidates, JDs, custom eval models with artifacts/rubric overrides, batches, reports, CV versions, and positioning sessions all have create/read/update paths plus async job handling. Gaps are mostly deletes and edits (no delete candidate, JD, context, or CV version; no update JD), which agents can work around.
Available Tools
78 toolsatlas_accept_candidate_search_declarationAInspect
Record the user's acceptance of the PDPA declaration for candidate search, kept as a legal record. Call ONLY after showing the user the exact declaration text and the user explicitly agreeing in this conversation (e.g. 'I agree'); never accept on their behalf or assume agreement. Free.
Inputs: user_agreed (required), declaration_version (required).
atlas_add_candidate_textAInspect
Add one candidate from CV text already in the chat, such as an attached CV you have read; no file or base64. Returns the candidate id (candidate_id); the CV is parsed in the background. For several CV files, use atlas_get_upload_link. Free.
Inputs: cv_text (required), context_id (required), candidate_name (required), tags, +1 more.
atlas_add_custom_eval_text_artifactCInspect
Teach a custom evaluation model with text, such as what good or bad looks like or scoring criteria, labelled strong, weak or mixed. Free.
Inputs: model_id (required), text_content (required), artifact_type (required), label, +1 more.
atlas_advisor_chatAInspect
Quick general hiring advice from Atlas Advisor (2 credits per message): no research, faster and cheaper than atlas_chat. Returns the reply and a conversation_id.
Inputs: message (required), conversation_id.
atlas_chatAInspect
Ask Atlas, CareerProof's workforce-intelligence AI (3 credits per message): researched answers with live tools (salary benchmarks, talent supply and demand, competitor intel). Returns the reply and a conversation_id. Can take 2-3 minutes.
Inputs: message (required), context_id, conversation_id.
atlas_clear_custom_eval_rubric_overridesADestructiveIdempotentInspect
Remove all of a custom evaluation model's rubric overrides, back to the inferred rubric. Free.
Inputs: model_id (required).
atlas_create_contextAInspect
Create a hiring context (a company or role) that holds candidates and JDs. Returns its id, the context_id the other atlas_* tools take. Reuse one from atlas_list_contexts if it exists. Free.
Inputs: company_name (required), industry, location, is_default, +3 more. Returns: id, role, industry, location, +11 more
atlas_create_custom_eval_modelAInspect
Create a custom evaluation model (your own scoring rubric) for a hiring context. Returns its id (model_id). Then teach it with artifacts and build its rubric with atlas_infer_custom_eval_rubric. Free.
Inputs: name (required), client_context_id (required), description.
atlas_create_jdBInspect
Save a job description (title and full text) in a hiring context. Free.
Inputs: title (required), content (required), context_id (required). Returns: id, title, source, content, +8 more
atlas_delete_custom_eval_modelBDestructiveIdempotentInspect
Delete a custom evaluation model with all its artifacts and rubric. Free.
Inputs: model_id (required).
atlas_download_reformatted_cvARead-onlyIdempotentInspect
A reformatted CV's PDF as base64 (very long: only when the user wants the file). Free.
Inputs: session_id (required).
atlas_download_reportARead-onlyIdempotentInspect
A completed Atlas report's PDF as base64, for programs that attach the file. To show or send the report to the user, give them dashboard_url and pdf_url from atlas_get_report instead. Free.
Inputs: report_id (required).
atlas_fit_match_enhancedBInspect
Fit match of one candidate against a job description, deepened with industry knowledge-base context (8 credits): fit score 0-100, strengths, gaps, recommendations, market context. Answers directly.
Inputs: jd_text (required), context_id (required), candidate_id (required).
atlas_generate_interviewCInspect
Interview questions tailored to a candidate, each with its rationale (8 credits). Answers directly.
Inputs: context_id (required), candidate_id (required), jd_text, num_questions, +1 more.
atlas_get_analysisARead-onlyIdempotentInspect
A completed analysis: scores, competency breakdown, recommendations. Free.
Inputs: analysis_id (required).
atlas_get_analyticsCRead-onlyIdempotentInspect
Talent analytics for a hiring context: candidate stats, analysis coverage, fit score distribution. Free.
Inputs: context_id (required). Returns: analyzed_count, avg_gem_scores, top_candidates
atlas_get_batch_gem_resultsARead-onlyIdempotentInspect
Per-candidate results of a completed batch GEM job: scores and competency breakdowns. Free.
Inputs: job_id (required).
atlas_get_batch_gem_statusARead-onlyIdempotentInspect
Progress of a batch GEM job: status (pending/running/completed/failed) and progress; a failed job has error_code and error_message. When completed, fetch atlas_get_batch_gem_results(job_id). To wait for it, prefer careerproof_wait(kind='batch_gem', id=job_id). Free.
Inputs: job_id (required).
atlas_get_candidateARead-onlyIdempotentInspect
One candidate in full: the parsed CV and parsing_status. Analyses need parsing_status='completed'. Free.
Inputs: context_id (required), candidate_id (required). Returns: id, tags, notes, source, +13 more
atlas_get_candidate_searchARead-onlyIdempotentInspect
One past candidate search: its candidates' labels and LinkedIn profiles and, for a Spotter email search, Spotter's reply with names and summaries (names are not kept for searches made here). Free.
Inputs: search_id (required).
atlas_get_candidate_search_declarationARead-onlyIdempotentInspect
Whether the user has accepted the PDPA declaration candidate search requires (one made by email with Spotter counts), with its exact text and version. Free.
Inputs: no named parameters.
atlas_get_custom_eval_batch_resultsARead-onlyIdempotentInspect
Per-candidate scores and dimension breakdowns of a completed custom evaluation batch. Free.
Inputs: batch_id (required).
atlas_get_custom_eval_batch_statusARead-onlyIdempotentInspect
Progress of a custom evaluation batch: status and progress. When completed, fetch atlas_get_custom_eval_batch_results(batch_id). To wait for it, prefer careerproof_wait(kind='custom_eval_batch', id=batch_id). Free.
Inputs: batch_id (required).
atlas_get_custom_eval_modelARead-onlyIdempotentInspect
One custom evaluation model in full: dimensions, weights, artifacts and rubric status. Free.
Inputs: model_id (required).
atlas_get_custom_eval_rubricBRead-onlyIdempotentInspect
A custom evaluation model's rubric: dimensions, scoring criteria and any overrides. Free.
Inputs: model_id (required).
atlas_get_dialogue_resultsCRead-onlyIdempotentInspect
A dialogue session's assessment: interview quality scores, communication, recommendations. Free.
Inputs: session_id (required).
atlas_get_jd_fit_batch_statusARead-onlyIdempotentInspect
Progress of a JD-Fit batch: status and progress. When complete, fetch atlas_get_jd_fit_results(context_id, batch_id). To wait for it, prefer careerproof_wait(kind='jd_fit_batch', id=batch_id, context_id=context_id). Free.
Inputs: batch_id (required), context_id (required).
atlas_get_jd_fit_resultsARead-onlyIdempotentInspect
JD-Fit results for a context: candidates ranked by fit score, with strengths and gaps. Pass batch_id for one run (default: the latest batch); include_all=true only if the user asks for every past run. Free.
Inputs: context_id (required), sort_by, batch_id, include_all.
atlas_get_reportARead-onlyIdempotentInspect
An Atlas report's status (pending/generating/completed/failed; a failed one has error_message), title, type and summary; once completed, dashboard_url and pdf_url to give the user. To wait for it, prefer careerproof_wait(kind='atlas_report', id=report_id). Free.
Inputs: report_id (required).
atlas_get_upload_linkAInspect
Get a 30-minute link to a page (no sign-in) where the user drags in many CVs (PDF, DOCX, DOC, TXT) at once: the fastest way to add CVs, for more than one CV or any file. Give the user the link; when they say they are done, call atlas_list_candidates. Free.
Inputs: context_id (required), max_files.
atlas_infer_custom_eval_rubricAInspect
Build a custom evaluation model's rubric (dimensions and scoring criteria) from its artifacts. Answers directly in 30-60 s. Free.
Inputs: model_id (required).
atlas_interview_followupCInspect
A probing follow-up question to a candidate's answer to an interview question (1 credit). Answers directly.
Inputs: context_id (required), candidate_id (required), candidate_answer (required), original_question (required), +1 more.
atlas_list_analysesBRead-onlyIdempotentInspect
List a candidate's analyses (id, type, status, scores). Free.
Inputs: context_id (required), candidate_id (required), analysis_type.
atlas_list_candidatesBRead-onlyIdempotentInspect
List a hiring context's candidates (id = candidate_id). Free.
Inputs: context_id (required).
atlas_list_candidate_searchesBRead-onlyIdempotentInspect
The user's past candidate searches, newest first, including Spotter email searches (channel 'email'). Free.
Inputs: limit, offset.
atlas_list_contextsBRead-onlyIdempotentInspect
List the user's hiring contexts (id = context_id). Free.
Inputs: include_inactive.
atlas_list_custom_eval_artifactsARead-onlyIdempotentInspect
List a custom evaluation model's artifacts (id, type, label, notes, status). Free.
Inputs: model_id (required).
atlas_list_custom_eval_modelsARead-onlyIdempotentInspect
List the user's custom evaluation models (id = model_id, name, description, status). Free.
Inputs: no named parameters.
atlas_list_cv_templatesARead-onlyIdempotentInspect
List saved branded CV templates (id = template_id, name, status), or with template_id one template's format: colours, fonts, section order. Free.
Inputs: context_id, template_id.
atlas_list_jdsARead-onlyIdempotentInspect
List a hiring context's job descriptions (id, title, content); the content is the jd_text the fit tools take. Free.
Inputs: context_id (required).
atlas_list_reportsARead-onlyIdempotentInspect
List the user's Atlas reports (id, type, status, title, summary; completed ones with dashboard_url and pdf_url). Free.
Inputs: no named parameters.
atlas_list_report_typesARead-onlyIdempotentInspect
The 16 Atlas research report types with their required and optional inputs and costs: the report_type values atlas_start_report takes. Free.
Inputs: no named parameters.
atlas_reformat_cvAInspect
Apply a saved branded CV template to a candidate's CV, producing a PDF (2 credits). Returns session_id for atlas_download_reformatted_cv. Templates are made on careerproof.ai (Atlas › CV Reformatter).
Inputs: template_id (required), candidate_id (required), context_id.
atlas_search_candidatesAInspect
Search 200M+ public professional profiles for candidates (the search Spotter runs). Returns ranked candidates with their LinkedIn profiles, a summary and how each matches the requirements. Costs 30 credits per candidate returned (none found = free; never more than the balance pays for): tell the user the most it can cost (limit x 30) and get a yes first. The first search needs the user's PDPA declaration: if the answer says so, follow it (show the exact text, get explicit agreement, then atlas_accept_candidate_search_declaration). Daily limits apply by plan.
Inputs: query (required), limit, skills, industry, +5 more.
atlas_set_custom_eval_rubric_overridesAIdempotentInspect
Override a custom evaluation model's inferred rubric (weights, dimension names, criteria) without re-inferring; replaces any earlier overrides. Free.
Inputs: model_id (required), overrides (required).
atlas_start_batch_gemAInspect
Start GEM analyses of several candidates (10 credits per candidate). Their CVs must be parsed. Returns job_id: check atlas_get_batch_gem_status(job_id), then atlas_get_batch_gem_results(job_id). Runs in the background: usually a few minutes, longer for large batches.
Inputs: context_id (required), candidate_ids (required), analysis_type.
atlas_start_custom_eval_batchAInspect
Start scoring several candidates with a custom evaluation model (5 credits per candidate). Returns batch_id: check atlas_get_custom_eval_batch_status(batch_id), then atlas_get_custom_eval_batch_results(batch_id). Runs in the background: usually a few minutes, longer for large batches.
Inputs: context_id (required), candidate_ids (required), custom_model_id (required), template_id, +1 more.
atlas_start_custom_eval_inferenceAInspect
Start generating a custom evaluation model's evaluation dimensions (5 credits). Returns task_id: check careerproof_task_status(task_id), then careerproof_task_result(result_type='custom_eval_inference', resource_id=model_id). Runs in the background: usually 1–3 minutes.
Inputs: model_id (required).
atlas_start_dialogue_assessmentAInspect
Start assessing the interview transcripts of an existing dialogue session (10 credits). Returns task_id: check careerproof_task_status(task_id), then atlas_get_dialogue_results(session_id). Runs in the background: usually 1–3 minutes.
Inputs: session_id (required).
atlas_start_fit_matchAInspect
Start a fit match of one candidate against a job description (8 credits). Returns task_id and analysis_id: check careerproof_task_status(task_id), then careerproof_task_result(result_type='fit_match', resource_id=analysis_id). Several candidates: atlas_start_fit_rank or atlas_start_jd_fit_batch. Runs in the background: usually 1–3 minutes.
Inputs: jd_text (required), context_id (required), candidate_id (required).
atlas_start_fit_rankAInspect
Start ranking 2 or more candidates against a job description (8 credits in all). Returns task_id and analysis_id: check careerproof_task_status(task_id), then careerproof_task_result(result_type='fit_rank', resource_id=analysis_id). Runs in the background: usually 1–3 minutes.
Inputs: jd_text (required), context_id (required), candidate_ids (required).
atlas_start_gem_analysisAInspect
Start a GEM competency analysis of one candidate: gem_full 10 credits, gem_lite 5, career_path 5. The CV must be parsed (atlas_get_candidate). Returns task_id and analysis_id: check careerproof_task_status(task_id), then atlas_get_analysis(analysis_id). Runs in the background: usually 1–3 minutes.
Inputs: context_id (required), candidate_id (required), analysis_type.
atlas_start_jd_analysisAInspect
Check a job description's text (5 credits): competitiveness, clarity, bias, salary benchmark, skills, suggested rewrites. Answers directly; needs no context.
Inputs: jd_text (required), industry_hint, location_hint, include_live_search.
atlas_start_jd_fit_batchAInspect
Start JD-Fit: match several candidates against one job description (3 credits per candidate). Returns batch_id: check atlas_get_jd_fit_batch_status(context_id, batch_id), then atlas_get_jd_fit_results(context_id, batch_id). Runs in the background: usually a few minutes, longer for large batches.
Inputs: context_id (required), candidate_ids (required), jd_title, jd_content, +1 more.
atlas_start_reportAInspect
Start a research report (15 credits). Take report_type and the inputs it requires from atlas_list_report_types first. Returns report_id: check atlas_get_report(report_id). Runs in the background: usually about 5 minutes, sometimes up to 10.
Inputs: inputs (required), report_type (required).
atlas_update_contextBIdempotentInspect
Update a hiring context; only the fields given change. Free.
Inputs: context_id (required), industry, location, is_active, +5 more. Returns: id, role, industry, location, +11 more
atlas_update_custom_eval_modelBIdempotentInspect
Update a custom evaluation model's name, description, dimensions or weights. Free.
Inputs: model_id (required), name, description, inferred_weights, +1 more.
atlas_upload_candidateAInspect
Add one candidate from a CV file sent as base64 (PDF/DOCX). Slow: for more than one CV, or any large file, use atlas_get_upload_link; for a CV already in the chat as text, use atlas_add_candidate_text. Returns the candidate id (candidate_id); the CV is parsed in the background. Free.
Inputs: file (required), context_id (required), tags, notes, +3 more.
atlas_upload_custom_eval_artifactBInspect
Teach a custom evaluation model with an example file (base64 PDF/DOCX), labelled strong, weak or mixed. Free.
Inputs: file (required), model_id (required), artifact_type (required), label, +2 more.
careerproof_task_resultARead-onlyIdempotentInspect
Result of a completed background task. resource_id by result_type: analysis, fit_match, fit_rank: analysis_id; batch_gem: job_id; report: report_id; custom_eval_inference: model_id; custom_eval_batch: batch_id; dialogue_assessment: session_id. jd_fit_batch takes context_id (and batch_id) instead. Free.
Inputs: task_id (required), result_type (required), batch_id, context_id, +1 more.
careerproof_task_statusARead-onlyIdempotentInspect
Progress of a background task: status queued/processing/retrying/completed/failed (retrying = still running) and progress_pct; a failed task has error_code and credits_refunded. When completed, fetch the result with careerproof_task_result. To wait for it, prefer careerproof_wait(kind='task', id=task_id). Free.
Inputs: task_id (required). Returns: result, status, task_id, error_code, +6 more
careerproof_waitARead-onlyIdempotentInspect
Wait for background work to finish, instead of checking its status repeatedly. Waits on CareerProof's side (up to 200 s) and answers as soon as it has finished or failed, or with the latest status if it is still running. kind: task (task_id from atlas_start_gem_analysis, fit match/rank, dialogue assessment, rubric inference), batch_gem (job_id), jd_fit_batch (batch_id + context_id), custom_eval_batch (batch_id), atlas_report or ceevee_report (report_id). Tell the user the work has started before you call it. Free.
Inputs: id (required), kind (required), context_id, max_wait_seconds.
ceevee_analyze_positioningAInspect
Positioning step 1 of 3 (5 credits, 20-30 s): how the market reads the CV: positioning snapshot, detected narrative lens, recruiter inference, mixed signals, and a session_id for ceevee_get_opportunities and ceevee_confirm_lens.
Inputs: cv_version_id (required), session_id.
ceevee_chatAInspect
Chat with CeeVee about the user's CV (2 credits per message): advice, edit suggestions, sources. Returns the reply and a conversation_id.
Inputs: message (required), cv_version_id (required), conversation_id.
ceevee_confirm_lensAInspect
Positioning step 3 of 3 (5 credits, 20-30 s): targeted CV edits for the lens the user chose, before/after with trade-offs, and PDF links. For richer edits pass what steps 1 and 2 returned (positioning_snapshot, detected_lens_full, recruiter_inference, selected_opportunities).
Inputs: cv_version_id (required), confirmed_lens (required), session_id, custom_positioning, +4 more.
ceevee_download_reportARead-onlyIdempotentInspect
A completed CeeVee report's PDF as base64, for programs that attach the file. To show or send the report to the user, give them dashboard_url and pdf_url from ceevee_get_report instead. Free.
Inputs: report_id (required).
ceevee_explain_changeBInspect
Why CeeVee recommends one edit, in detail (1 credit).
Inputs: change_id (required), cv_version_id (required).
ceevee_full_reviewAInspect
Full CV review in one call (10 credits, 30-60 s): positioning, lens, targeted edits with trade-offs and, optionally, career opportunities. The one-call alternative to the 3 positioning steps.
Inputs: cv_version_id (required), jd_text, session_id, requested_lens, +1 more.
ceevee_generate_reportAInspect
Start a CeeVee career-intel report (15 credits). Most types need cv_version_id or inputs.role_title. Returns report_id: check ceevee_get_report(report_id). Runs in the background: usually about 3 minutes.
Inputs: report_type (required), inputs, cv_version_id.
ceevee_get_opportunitiesAInspect
Positioning step 2 of 3 (3 credits): 2-4 career moves for a narrative lens, with rationale, CV signals and market context.
Inputs: lens (required), cv_version_id (required), session_id.
ceevee_get_positioning_sessionBRead-onlyIdempotentInspect
One positioning session in full: analysis, lens, opportunities, targeted edits, PDF links. Free.
Inputs: session_id (required). Returns: id, created_at, edits_json, updated_at, +11 more
ceevee_get_reportARead-onlyIdempotentInspect
A CeeVee report's status (pending/processing/completed/failed; a failed one has error_message), title, type, inputs and summary; once completed, dashboard_url and pdf_url to give the user. To wait for it, prefer careerproof_wait(kind='ceevee_report', id=report_id). Free.
Inputs: report_id (required).
ceevee_get_versionBRead-onlyIdempotentInspect
One CV version in full: structured content, sections, word count, audience profile. Free.
Inputs: cv_version_id (required). Returns: id, name, status, is_main, +13 more
ceevee_list_positioning_sessionsARead-onlyIdempotentInspect
List the user's positioning sessions (id, status, cv_version_id, created_at). Free.
Inputs: no named parameters.
ceevee_list_reportsBRead-onlyIdempotentInspect
List the user's CeeVee reports (id, type, status, title, summary; completed ones with dashboard_url and pdf_url). Free.
Inputs: limit, offset, status.
ceevee_list_report_typesARead-onlyIdempotentInspect
List report types with their required inputs and credit costs. Free.
Inputs: no named parameters.
ceevee_list_versionsARead-onlyIdempotentInspect
List the user's CV versions (id = cv_version_id, filename, created_at, main_version). Free.
Inputs: no named parameters.
ceevee_upload_cvAInspect
Upload the user's own CV (base64 PDF/DOCX) as a new CV version; returns its id (cv_version_id) and parsed sections. Free.
Inputs: file (required), filename.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
# **RChilli** RChilli MCP Hub is a production-grade Model Context Protocol (MCP) server that exposes RChilli’s HR data intelligence platform through AI-callable tools. Built on 15+ years of HR data intelligence, RChilli supports ATS vendors, HR technology platforms, staffing agencies, and enterprise recruiting teams worldwide. The tools return consistent, structured JSON responses for recruiting, talent intelligence, skills, matching, compliance, and HR workflow use cases. `userkey` and `subuserid` are injected automatically from the Bearer token and must not be passed manually. <br> --- <br> # **Available Tools** <br> > ### **`analyze_hr_call`** > > Transcribes and analyzes HR or recruiting call recordings to extract speaker turns, sentiment, candidate intent, action items, skill mentions, and structured follow-up data for recruiting operations. <br> > ### **`analyze_skill_adjacency`** > > Identifies related, adjacent, and transferable skills to support skill discovery, talent mobility, workforce planning, and candidate evaluation. <br> > ### **`analyze_skill_gap`** > > Compares candidate or employee skills against a target job and returns present skills, missing skills, readiness score, and development areas for hiring, internal mobility, and workforce planning. <br> > ### **`autocomplete_job_profile`** > > Accepts a partial job title and returns ranked autocomplete suggestions with canonical titles and job families. Ensures job titles map to standardized taxonomy profiles from the moment a recruiter starts typing. <br> > ### **`autocomplete_skill`** > > Accepts a partial skill string and returns ranked autocomplete suggestions with canonical skill names and categories. Helps prevent free-text entry errors and keeps skill data clean. <br> > ### **`classify_job_zone`** > > Reads the job profile from a resume or job description and returns its O*NET Job Zone, from Zone 1 through Zone 5, based on the education, experience, and training preparation required for the role. <br> > ### **`convert_document_format`** > > Accepts a document as base64 or URL and converts between PDF, DOCX, RTF, HTML, and plain text. Useful as a pre-processing step before extracting data from non-standard document formats. <br> > ### **`detect_bias`** > > Reviews job descriptions and hiring criteria for gendered language, age-coded terms, unnecessary credential inflation, cultural exclusion signals, and related compliance risks. Suggests neutral replacements. <br> > ### **`detect_resume_suspicion`** > > Reviews candidate profile data for possible inconsistencies, unusual claims, timeline conflicts, missing context, and other signals that require recruiter review. <br> > ### **`extract_contacts`** > > Identifies and structures names, emails, phone numbers, LinkedIn URLs, and addresses with field-level confidence scores from candidate records, emails, or documents. <br> > ### **`extract_job_data`** > > Extracts and converts job descriptions into structured hiring data including job title, required skills, preferred skills, responsibilities, experience, education, and taxonomy-normalized role requirements. <br> > ### **`extract_resume_data`** > > Extracts and converts resumes, CVs, and candidate documents into structured, searchable profiles with contact details, skills, experience, education, certifications, and taxonomy-enriched data for ATS, HCM, and AI recruiting workflows. Supports multilingual extraction, batch processing, resume auto-fill, and reprocessing of historical resumes. <br> > ### **`extract_resume_data_from_url`** > > Accepts a direct URL to a PDF, DOCX, or RTF file and returns the same normalized JSON profile as Resume Data Extraction. Ideal for resumes stored in cloud storage, S3, email attachments, or other URL-accessible sources. <br> > ### **`find_matches_in_index`** > > Accepts a resume or job description as input and returns the top matching documents from the indexed corpus, ranked by semantic similarity. <br> > ### **`generate_interview_questions`** > > Creates technical, behavioral, situational, and competency-based interview questions tailored to a role and candidate profile, including question type, competency, and expected answer signals. <br> > ### **`generate_jd`** > > Generates structured job descriptions with title, responsibilities, required skills, preferred skills, qualifications, tone alignment, language support, and inclusivity scoring from role inputs. <br> > ### **`geolocate`** > > Converts partial or informal location text into structured city, state, country, ISO codes, latitude, and longitude. Supports radius-based candidate search and workforce planning. <br> > ### **`index_document`** > > Indexes a resume or job description in RChilli Search & Match so it can be searched, matched, updated, and reused across candidate matching, job matching, and similarity-search workflows. <br> > ### **`lookup_job_profile`** > > Returns authoritative detail for a known job profile including canonical title, SOC/O*NET code, job family, typical required and preferred skills, salary bands, and work context. <br> > ### **`lookup_skill`** > > Returns authoritative detail for a known skill including description, aliases, related skills, proficiency levels, and O*NET or ESCO mappings. <br> > ### **`map_job_to_skills`** > > Converts job descriptions into granular skill maps with required and preferred skill clusters, proficiency signals, taxonomy tags, and downstream matching attributes. <br> > ### **`match_end_to_end`** > > Orchestrates data extraction, indexing, taxonomy normalization, and matching to return ranked candidates or jobs with scores, explainable results, and an audit trail from a single call. <br> > ### **`normalize_candidate_data`** > > Cleans and normalizes candidate records from multiple ATS or HR systems, resolves field conflicts, deduplicates records, and produces standardized candidate data with a field-level change log. <br> > ### **`normalize_hr_data_with_lov`** > > Maps raw and inconsistent HR data values, including degrees, universities, certifications, job profiles, skills, and locations, to the closest configured List of Values entry with a standardized value and confidence score. <br> > ### **`recommend_learning_path`** > > Builds structured learning paths with prerequisites, skill sequence, certifications, proficiency targets, and LMS alignment based on a person’s profile and target role. <br> > ### **`redact_resume`** > > Redacts configured personally identifiable information from candidate profiles to support anonymized review, bias-aware screening, compliance workflows, and audit logs. <br> > ### **`reformat_resume_with_template`** > > Applies one of the RChilli resume templates, TM001 through TM006, to a structured candidate profile and produces a consistently formatted PDF, DOCX, RTF, or HTML document. <br> > ### **`score_resume_against_jd`** > > Accepts one resume and one job description and returns an overall match score, dimension scores, matched skills, skill gaps, and a natural-language explanation. No index is required. <br> > ### **`screen_application_batch`** > > Evaluates a batch of candidates against job requirements and custom criteria, returning scores, insights, skill gaps, and recommended next actions for each candidate. <br> > ### **`search_indexed_documents`** > > Accepts a query string and returns ranked document references from the tenant’s indexed corpus. Supports Boolean and semantic search modes. <br> > ### **`skill_mapping`** > > Maps raw skill text to standardized RChilli taxonomy skills, aliases, classifications, and related skill information. <br> > ### **`tag_entities`** > > Annotates extracted HR text by wrapping recognized entities in structured XML-style labels. Supported entities include job titles, skills, names, degrees, organizations, locations, countries, dates, and years.
The career management plugin for your own AI assistant: CVs, cover letters, interviews and more.
Query professional profiles, search candidates, and get AI-powered summaries and job fit analysis.
100+ MCP tools for AI agents: content metadata, trade intelligence, business-expertise analysis.
Related MCP Servers
- AlicenseAqualityDmaintenanceManage Job using MCP: Manage Job, Candidates, Resumes, Salaries all within this one MCP tools It can solve problems like: You have 50 resumes to screen. Your AI assistant can reason about candidates, but it can't: Read PDFs/DOCX — The AI can't open binary files Extract structured data — Copy-pasting loses formatting, metrics, and context Compare at scale — No consistent scoring across candida2485 npm1MIT
- AlicenseBqualityDmaintenanceProvides access to 47 AI-powered career tools for resume building, job tracking, ATS optimization, and interview coaching. It enables users to manage their job search, research companies, and negotiate salaries directly through an MCP-compatible AI assistant.558 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to serve as a personal career analyst by searching, matching, and explaining job recommendations, managing job applications, and syncing public job boards through standardized MCP tools.MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.