mcp-server-cv-modify
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NODE_ENV | No | Node environment (e.g., production, development). | production |
| LOG_LEVEL | No | Logging level (e.g., debug, info, error). | info |
| CACHE_ENABLED | No | Enable caching of scraping results (true/false). | true |
| CACHE_TTL_HOURS | No | Time-to-live for cache entries in hours. | 24 |
| DETECT_LANGUAGE | No | Enable automatic language detection (true/false). | true |
| NLP_MAX_KEYWORDS | No | Maximum number of keywords to extract. | 50 |
| EMBED_RTL_MARKERS | No | Embed Unicode RTL markers in output (true/false). | true |
| BROWSER_TIMEOUT_MS | No | Timeout in milliseconds for browser operations. | 30000 |
| PLAYWRIGHT_HEADLESS | No | Run Playwright browser in headless mode (true/false). | true |
| SCRAPER_MIN_DELAY_MS | No | Minimum delay in milliseconds between scraping requests (to avoid detection). | 5000 |
| NLP_MIN_KEYWORD_SCORE | No | Minimum score threshold for keyword extraction (0-1). | 0.3 |
| SCRAPER_MAX_CONCURRENT | No | Maximum number of concurrent scraping operations. | 1 |
| NORMALIZE_HEBREW_SPACING | No | Normalize spacing for Hebrew text (true/false). | true |
| CV_MAX_KEYWORDS_PER_BULLET | No | Maximum number of keywords to add per bullet point. | 2 |
| USE_HEBREW_CHARACTER_WIDTHS | No | Use Hebrew character widths for formatting (true/false). | true |
| CV_MODIFICATION_CONFIDENCE_THRESHOLD | No | Confidence threshold for CV modifications (0-1). | 0.6 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_job_descriptionA | Extracts job description and keywords from a LinkedIn or job posting URL. Scrapes the job posting, extracts key information, and identifies important keywords and skills. |
| modify_cvA | Modifies a CV to better match a job description by strategically emphasizing relevant keywords. Parses the CV, extracts keywords from the job posting, and enhances the CV with relevant keywords while maintaining naturalness. |
| analyze_cv_job_matchA | Analyzes how well a CV matches a job description without modifying it. Scores the CV against job requirements and provides specific improvement suggestions. |
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 3 tools
Each tool addresses a distinct stage in the CV optimization workflow: extracting job data, modifying the CV, and analyzing match. No two tools perform overlapping functions, so there is no ambiguity in selection.
All tool names follow a consistent verb_noun pattern with underscore separators (extract_job_description, modify_cv, analyze_cv_job_match). The naming is clear and predictable, making it easy for an agent to infer each tool's purpose.
The server has 3 tools, which is within the typical well-scoped range. Each tool is essential to the CV modification workflow, and the small count reflects a focused design without unnecessary bloat.
The tools cover the core pipeline from job description extraction to CV modification and match analysis. However, there are minor gaps such as no explicit tool for reverting changes or handling multiple CV formats, which agents might need to work around.