resume-kit-mcp
This MCP server lets an AI assistant manage, validate, build, and score tailored resume versions from a shared fact library without inventing facts.
List resume versions, their titles/applied dates, and the active content directory.
Show a version's resolved plain text as it will appear in the PDF.
Run fact guardrails on one or all versions to catch forbidden claims and missing required facts.
Build a version to .docx and .pdf, check the page target, and report overflow text.
Score a built resume against job postings, returning scores, must-haves met, gaps, and per-requirement verdicts; real gaps are flagged.
Retrieve standard application-form answers by section or all at once.
Get ATS-specific quirks, shared rules, and JavaScript helpers for systems like Greenhouse, Ashby, Taleo, Workday, LinkedIn, and Eightfold.
Provides quirks, shared rules, and JavaScript helpers for the Greenhouse applicant tracking system, helping map application form fields, handle React-controlled inputs, and identify required fields when filling out job applications.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@resume-kit-mcp score my acme resume against its posting and flag real gaps"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
resume-kit
Tailored resume versions from one fact library, with guardrails that keep them honest.

You keep every confirmed fact about your career in one file. Each job gets a short version file that picks and orders those facts, with its own headline and summary. resume-kit renders a version to .docx and .pdf, checks that it hits your page target, and won't build anything that breaks one of your guardrails: claims you've ruled out, or facts that must always appear. It can also score a version against a job posting with shortlist-ai, the way a screener would read it. All of this is also an MCP server, so an AI assistant can tailor, build, and score resumes for you without making things up.
Why
Tailoring a resume for every job tends to produce a dozen near-copies that drift apart. A number gets corrected in one copy but not the others. A claim you walked back reappears. Page 3 appears without anyone noticing. With resume-kit:
Each fact lives in one place. Versions refer to facts by id and never restate them, so a correction reaches every version.
Guardrails fail the build.
guardrails.yamllists claims that must never appear (with the reason) and facts that must. They're checked on every build, which also makes it safe to let an AI assistant write versions.The page count is checked. The build fails unless the PDF hits its target, and it prints the text that spilled over.
Gaps get sorted.
resume scorelists the must-haves a posting asks for that the resume doesn't show. A gap that matches a guardrail is labeled as a real gap, not a wording problem to paper over.
Related MCP server: WebMCP
Setup
git clone https://github.com/vinayvobbili/resume-kit && cd resume-kit
python3 -m venv .venv && .venv/bin/pip install -e '.[dev]'
npm install # docx-js, used by the renderer
brew install --cask libreoffice && brew install poppler # PDF conversion and page checksTry it on the bundled example (a fictional candidate):
resume --content examples/content build --all --out /tmp/resumesYour content
Content lives outside this repo, so your personal data never ends up in it:
cp -R examples/content ~/resume-content # then replace the facts with yours
mkdir -p ~/.config/resume-kit && ln -s ~/resume-content ~/.config/resume-kit/contentresume-kit looks in the --content flag, then $RESUME_KIT_CONTENT, then ~/.config/resume-kit/content, and falls back to the example (and says so). Keep answers.yaml out of version control.
Commands
resume list # versions, the content dir in use, and applied dates
resume draft acme-sre posting.md # draft a tailored version from a posting
resume check # guardrails on every version
resume build acme --preview # -> ~/Downloads/<output>.{docx,pdf}
resume score acme # score against the version's postingshow, diff, facts, trace, answers and ats are in the guide, along with the options a version can set (extends, drop, undated, waive, copy_to and more), how drafting and since: guardrails work, scoring backends, the MCP tools and the ATS notes.
MCP server
claude mcp add resume-kit -s user -- /path/to/resume-kit/.venv/bin/resume-kit-mcpIts instructions tell the assistant never to add unconfirmed facts, and never to "close" a gap that a guardrail marks as real.
Tests
pytest -m "not render" is fast; pytest also renders the examples. scripts/check runs what CI runs. Tests only use the fictional example content.
License
MIT
Available Tools
7 toolsapplication_answersB
Standard answers for application forms: contact, work_authorization, experience_years, screening, salary, defaults, eeo. Omit section for everything.
Inputs: section.
ats_playbookC
Quirks, shared rules, and JavaScript helpers for an applicant tracking system (greenhouse, ashby, taleo, workday, linkedin, eightfold) or a job-page host.
Inputs: system (required).
build_versionC
Render .docx and .pdf (default ~/Downloads), check the page target, report overflow text.
Inputs: version (required), out_dir, with_preview.
check_factsC
Run the fact guardrails (forbidden claims, required facts) on one version or all of them.
Inputs: version.
list_versionsB
List resume versions with their title and applied date, and the content directory in use.
Inputs: no named parameters.
score_versionA
Score the built resume against job postings (file paths; default: the version's posting) with shortlist-ai. Returns per-job score, must-haves met, gaps, and per-requirement verdicts with quotes. gap_notes marks gaps that a guardrail says are real, which must not be papered over.
Inputs: version (required), backend, postings.
show_versionD
The resolved resume as plain text (what the PDF will say).
Inputs: version (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Most tools target clearly distinct actions: list_versions (enumerate), show_version (preview text), build_version (render files), check_facts (guardrails), score_version (job matching), application_answers (form data), ats_playbook (reference). There is mild conceptual overlap between show_version/build_version (both produce the resume) and between check_facts/score_version (both validate against requirements), but the descriptions distinguish internal guardrails from external scoring well enough.
Five of seven tools follow a clean verb_noun pattern (list_versions, show_version, check_facts, build_version, score_version). The remaining two (application_answers, ats_playbook) are noun phrases rather than verb-led, a minor deviation that still reads clearly.
Seven tools is well-scoped for a resume-tailoring workflow, and each tool maps to a distinct step (list, preview, validate, build, score, form answers, ATS guidance). No redundant or filler tools.
The surface covers the consume/validate/build/score lifecycle plus application-form and ATS support, which is strong for the stated purpose. The main gap is authoring: there is no create/update/delete for versions or content, so resume editing must happen outside the server (implied by the 'content directory' model), a minor workaround.
Maintenance
Related MCP Connectors
Resume builder with native MCP — create and edit resumes from your AI assistant.
Build, improve and share your resume, and run your job search, from your AI assistant.
Score resumes, screen candidates by phone, and check references from your AI assistant.
Store your CV once, then get tailored .docx resumes, cover letters and keyword gaps for a job.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables evidence-grounded resume tailoring by generating ATS-readable LaTeX/PDF resumes from a user-curated experience bank, with every bullet traceable to evidence and inferred wording flagged for user approval.MIT
- AlicenseNot gradedqualityBmaintenanceEnables an AI agent to work inside a resume workspace where it can search job postings and propose edits grounded in user-recorded facts, while the interface constrains its tools and requires human approval before any change or application is prepared.15 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to tailor a resume to any job description by extracting keywords, analyzing gaps and ATS compliance, managing versions, and compiling PDF/LaTeX outputs entirely locally without external API keys.MIT

Civify MCP Serverofficial
AlicenseAqualityBmaintenanceEnables AI agents to parse resumes, tailor CVs, score ATS compatibility, redact PII, scrape job postings, and track applications through a career platform.823 npmAGPL 3.0