LaTeX Resume MCP
Enables creating, editing, and compiling LaTeX resumes directly from Claude using built-in templates, with support for managing multiple resume files and automatic PDF generation.
README
LaTeX Resume MCP
An MCP (Model Context Protocol) server that lets you create, edit, and compile LaTeX resumes directly from Claude.
Features
- Create resumes from built-in templates (modern, classic, minimal)
- Edit resumes with full replacement or targeted find/replace
- Compile to PDF using pdflatex (requires LaTeX installation)
- Add experience/education entries with structured commands
- List and manage multiple resume files
- Observability tools - Analyze LaTeX for errors, inspect PDFs, verify formatting
Installation
Using uvx (recommended)
uvx latex-resume-mcp
Using pip
pip install latex-resume-mcp
Configuration
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Using uvx
{
"mcpServers": {
"latex-resume": {
"command": "uvx",
"args": ["latex-resume-mcp"]
}
}
}
Using pip installation
{
"mcpServers": {
"latex-resume": {
"command": "latex-resume-mcp"
}
}
}
Custom directories (optional)
{
"mcpServers": {
"latex-resume": {
"command": "uvx",
"args": ["latex-resume-mcp"],
"env": {
"LATEX_RESUME_DIR": "/path/to/your/resumes",
"LATEX_TEMPLATES_DIR": "/path/to/your/templates"
}
}
}
}
Prerequisites for PDF Compilation
To compile resumes to PDF, you need LaTeX installed:
macOS:
brew install --cask mactex
# or for a smaller installation:
brew install --cask basictex
Ubuntu/Debian:
sudo apt install texlive-latex-base texlive-latex-extra
Fedora:
sudo dnf install texlive-scheme-basic
Windows: Download and install MiKTeX
Available Tools
Resume Management
| Tool | Description |
|---|---|
list_resumes |
List all resume files |
read_resume |
Read a resume's content |
create_resume |
Create a new resume |
edit_resume |
Edit an existing resume |
delete_resume |
Delete a resume |
compile_resume |
Compile to PDF |
Templates
| Tool | Description |
|---|---|
list_templates |
Show available templates |
get_template |
Get template content |
add_experience |
Add work experience |
add_education |
Add education entry |
Observability & Verification
| Tool | Description |
|---|---|
analyze_latex |
Check LaTeX for syntax errors, placeholder text, long lines |
inspect_pdf |
Extract text from PDF, check page count, verify content |
check_compilation_log |
Parse log for overfull boxes, warnings, errors |
compile_and_verify |
Compile + run all checks in one step |
get_config |
Show current configuration |
Usage Examples
Once configured, you can use natural language in Claude:
- "Create a new resume called software_engineer using the modern template"
- "Add my experience at Google as a Senior Engineer from 2020 to present"
- "Update my resume to change the email to newemail@example.com"
- "Compile my resume and check for any issues"
- "Analyze my resume for formatting problems"
- "List all my resumes"
Observability Example
The compile_and_verify tool runs a complete check:
> Compile and verify my resume
✓ LaTeX Analysis: 2 warnings (placeholder text found)
✓ Compilation: Success
✓ PDF Inspection: 1 page, 2847 characters extracted
✓ Log Check: No overfull boxes
Status: success_with_warnings
PDF: ~/.latex-resumes/resumes/my_resume.pdf
Templates
Modern
Clean, professional design with color accents and structured formatting. Best for tech roles.
Classic
Traditional resume format with clear sections and horizontal rules. Good for conservative industries.
Minimal
Simple, no-frills layout focusing purely on content. Great for academic or research positions.
Default Directories
Resumes are stored in ~/.latex-resumes/resumes/ by default. You can customize this with the LATEX_RESUME_DIR environment variable.
Optional: PDF Text Extraction
For full PDF inspection (text extraction, page count), install poppler:
macOS:
brew install poppler
Ubuntu/Debian:
sudo apt install poppler-utils
This enables the inspect_pdf tool to extract and verify text content from compiled PDFs.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。