cv-tailor-mcp

An MCP server that tailors a one-page LaTeX CV to a specific job posting without burning tokens on repetitive work: re-reading your whole CV source, writing the same LaTeX boilerplate over and over, or pasting pdflatex compiler logs into the chat.

It works identically from Claude Code and Cursor (or any other MCP-compliant client) -- MCP is an open protocol, so the same server binary is just registered in each client's own config file.

This repo contains no personal data. You keep your own cv_facts.yaml (your real experience/projects/skills) in your own private repo, and point this server at it via environment variables. See cv_tailor_mcp/examples/cv_facts.example.yaml for a fictional but complete example, and docs/SCHEMA.md for the full schema.

What it does

Instead of:

1. Reading your entire CV source file into the model's context every time,

2. reading a previous tailored variant as a style reference,

3. having the model write ~150-250 lines of near-identical LaTeX by hand, and

4. pasting compiler output into the chat 3-5 times while manually tightening spacing to fit one page...

...you get a small set of tool calls:

render_and_compile tries default, compact, and tight spacing when spacing_profile is auto, then returns paths, page count, the selected profile, and structured diagnostics.

Related MCP server: LaTeX Resume MCP

Install

Requires Python 3.10+. A LaTeX distribution is optional during setup: without pdflatex, the MCP can still generate .tex files and reports a clear error if compile_cv is called.

git clone https://github.com/AaronUgalde/cv-tailor-mcp.git
cd cv-tailor-mcp
./setup.sh

The setup script:

1. Installs the command in a project-local virtual environment.

2. Creates ~/.cv-tailor/cv_facts.yaml with fictional starter data.

3. Creates ~/.cv-tailor/generated/.

4. Safely adds cv-tailor to ~/.cursor/mcp.json, preserving other servers.

It never replaces an existing facts file or cv-tailor MCP entry unless you explicitly choose the corresponding --force-facts or --force-config flag.

Next, replace the fictional information in ~/.cv-tailor/cv_facts.yaml, restart Cursor, and ask it to call list_tags.

Install as a user command

Install the published PyPI package as an isolated command with:

uv tool install cv-tailor-mcp
cv-tailor-mcp init

pipx install cv-tailor-mcp works as an alternative to uv.

Useful setup options:

cv-tailor-mcp init --no-cursor
cv-tailor-mcp init --facts-path ~/private-cv/facts.yaml --output-dir ~/CVs
cv-tailor-mcp init --force-config       # never overwrites facts
cv-tailor-mcp init --force-facts        # explicit facts reset
cv-tailor-mcp configure --client all --facts-path ~/private-cv/facts.yaml --output-dir ~/CVs
cv-tailor-mcp configure --client all --project-dir ~/my-cv --force-config
cv-tailor-mcp doctor

configure updates or migrates Cursor and Claude MCP entries without creating or changing CV facts. Existing configuration files are backed up before a write, and unrelated MCP servers and custom environment values are preserved. Use --cursor-config or --claude-config for non-default locations.

cv-tailor-mcp serve starts the stdio server and is normally invoked by Cursor rather than run manually.

Configuration

Environment variables

The server fails fast if the facts or output paths are missing. A missing pdflatex only disables compile_cv; all other tools remain available.

Other MCP clients can use the command and environment variables generated in Cursor's mcp.json. The transport is standard MCP over stdio.

Example session

> list_tags
{"tags": [{"name": "backend", "experience": 1, "projects": 1, ...}, ...]}

> get_facts(tags=["backend", "cloud"])
{... only the entries/bullets tagged backend or cloud ...}

> render_and_compile({
    "variant": "acme",
    "tagline": "Backend Engineering Intern Candidate & Cloud",
    "summary": "Plain text is escaped safely by default.",
    "education": [{
      "id": "edu_utaustin",
      "header_override": {"graduation": "Expected Graduation: December 2027"}
    }],
    "skill_group_ids": ["languages", "backend_cloud"],
    "experience": [{
      "id": "acme_backend_intern",
      "bullet_ids": ["acme_api_bullet", "acme_pipeline_bullet"],
      "bullet_overrides": {
        "acme_api_bullet": "Tailored plain-text wording with 25% improvement."
      },
      "extra_bullets": [{"latex": "Explicit raw \\textbf{LaTeX} opt-in."}]
    }],
    "projects": [{
      "id": "proj_taskflow",
      "bullet_ids": ["taskflow_realtime_bullet"],
      "header_override": {"subtitle": "Distributed Systems Project"}
    }],
    "spacing_profile": "auto"
  })
{"success": true, "tex_path": ".../cv_acme.tex", "pdf_path": ".../cv_acme.pdf",
 "pages": 1, "spacing_profile": "default", "diagnostics": []}

Bring your own template

If the bundled one-page style doesn't match yours, write your own .tex.j2 (Jinja2, using << >> for variables and <% %> for blocks/loops instead of the default {{ }}/{% %}, since LaTeX already uses {/}) and point CV_TEMPLATE_PATH at it. It must accept the same context documented in docs/SCHEMA.md -- see cv_tailor_mcp/templates/default_cv_template.tex.j2 for a working reference.

Safety model

• cv_facts.yaml remains immutable from the MCP's perspective. Education, experience, project, and bullet overrides exist only in the generated CV.

• Existing YAML text remains trusted LaTeX for backward compatibility. New request text is plain and escaped by default; raw LaTeX requires {"latex": "..."}.

• Output validation reports malformed commands, placeholders, missing sections, page-count problems, and suspicious PDF whitespace. Always review the final PDF before submitting it.

License

MIT, see LICENSE.