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:

There's no automatic "shrink until it fits one page" tool in v1 -- if compile_cv reports 2 pages, call render_cv again with spacing_profile: "compact" or "tight" (see docs/SCHEMA.md).

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 pass --force.

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

The project is packaged for PyPI. After publishing it, users can install it 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 doctor

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_cv({
    "variant": "acme",
    "tagline": "Backend Engineering Intern Candidate",
    "summary": "...",
    "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, LaTeX-ready wording for this CV only."
      }
    }],
    "projects": [{"id": "proj_taskflow", "bullet_ids": ["taskflow_realtime_bullet"]}]
  })
{"tex_path": ".../cv_acme.tex", "line_count": 118, "spacing_profile": "default"}

> compile_cv("acme")
{"success": true, "pages": 1, "first_error": null}

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.

Scope / non-goals for v1

• No auto-fit-to-one-page spacing tool -- three manual spacing_profile presets instead (see above).
• cv_facts.yaml remains the immutable source of truth from the MCP's perspective. render_cv can tailor selected bullets through bullet_overrides, but those rewrites only affect the generated CV.
• compile_cv only confirms the page count pdflatex reports -- it doesn't check whether the result looks good. Open the PDF yourself before you send it anywhere.

License

MIT, see LICENSE.