matchcv-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MATCHCV_BASE_URL | No | API origin. Only needed to point at a development deployment. | https://matchcv.co |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ats_checkA | Score resume text for applicant tracking system (ATS) compatibility. Returns a 0-100 score, a recruiter take, prioritized issues with concrete fixes, and detected strengths. Use for "is my resume ATS friendly", "why am I not getting interviews", or before tailoring to a specific job. |
| analyze_job_descriptionA | Parse a job posting into structured data: title, company, seniority, industry, must-have keywords, nice-to-have keywords, and key responsibilities. Feed the result into optimize_resume to find keyword gaps. |
| optimize_resumeA | Return prioritized, rewrite-level suggestions for a resume, optionally aimed at a specific role or job description. Each suggestion has a type, priority, tip, and an example rewrite. Pass missingMustHave / missingNiceToHave from analyze_job_description to close keyword gaps. |
| roast_resumeA | Run the MatchCV "resume roast": a brutally honest recruiter reaction plus an ATS score. Returns a public shareable report URL. Use when the user wants candid feedback rather than a polite checklist. |
| extract_resume_textA | Read a local PDF/DOC/DOCX/TXT resume and return its plain text, optionally also parsing it into structured JSON (name, experience, education, skills). Text extraction is unlimited; set structured=true only when the structured form is needed, since that path uses a daily AI credit. Scanned/image-only PDFs will fail — ask the user to paste the text instead. |
| tailor_resumeA | The full MatchCV pipeline: analyze the job description, structure the resume, then rewrite it for that role with must-have keywords worked in and bullets rewritten. Returns the tailored resume JSON, an ATS score, and a public preview link the user can open and download as PDF. This is the heaviest tool — it uses one generation credit plus the parse and JD-analysis credits, so run it once the user has settled on a target job. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Most tools map to a distinct pipeline stage: extract, analyze, optimize, tailor. ats_check and roast_resume overlap somewhat since both return ATS scores and recruiter feedback, but their descriptions clearly separate polite actionable feedback from a candid shareable roast, and optimize_resume vs tailor_resume are differentiated by suggestion-level vs full rewrite.
All tool names use lowercase snake_case and mostly follow an imperative verb_noun pattern: analyze_job_description, optimize_resume, extract_resume_text, tailor_resume. ats_check is the only deviation, reading more like a noun phrase than check_ats, but the overall naming remains predictable and readable.
Six tools is a well-scoped size for a resume/CV assistant, covering input extraction, job description parsing, ATS feedback, optimization, roasting, and full tailoring. Each tool has a clear role in the workflow, and there is no sense of bloat or excessive granularity.
The tool surface covers the core resume workflow end to end: extract text, parse job descriptions, diagnose ATS issues, suggest improvements, and generate a fully tailored resume with a preview link. There are no obvious dead ends, and the descriptions include appropriate guidance for handling limitations such as scanned PDFs or AI credit usage.