StoryLenses — AI Cover Letter Engine for Agents
About
The first production MCP server for job applications. 5 composable tools that analyze job postings, match candidate profiles, generate story-driven cover letters using 15+ narrative archetypes, and quality-score results. Supports English, German, Spanish, and Portuguese.
Details
- Author
- benediktgirz
- Downloads
- 378
- Categories
- Other, AI
Jump to
- 5 tools: analyze job, match profile, generate letter, quality check, list archetypes
- Extract 15+ structured fields from any job posting
- Match CV against job data with fit score and narrative angle
- Generate story-driven letters using 15+ narrative archetypes
- Score letters 0–100 across four quality pillars
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
StoryLenses — AI Cover Letter Engine for AgentsCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Obtain a free API key at https://www.storylenses.app/developers (10 generations/month, no credit card). Then configure your agent to call any of the five tools: analyze a job posting, match a CV, generate a letter, quality-check a letter, or list available narrative archetypes.
storylenses_analyze_job
Extract 15+ structured fields from a job posting — role requirements, company challenges, culture signals, recruiter priorities
storylenses_match_profile
Match a candidate profile/CV against job data — identifies fit score, matching skills, career gaps, and strongest narrative angle
storylenses_generate_letter
Generate a story-driven cover letter using matched data and a narrative archetype. Supports en/de/es/pt.
storylenses_quality_check
Score and evaluate a cover letter for relevance, narrative strength, and completeness. Returns score 0-100 with actionable feedback.
storylenses_list_archetypes
Return available narrative archetypes with descriptions so the agent or user can select a style
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"storylenses \u2014 ai cover letter engine for agents": {
"storylenses": {
"command": "npx",
"args": [
"-y",
"@storylenses/mcp-server"
],
"env": {
"STORYLENSES_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
}
McpServers
{
"storylenses": {
"command": "npx",
"args": [
"-y",
"@storylenses/mcp-server"
],
"env": {
"STORYLENSES_API_KEY": "<YOUR_API_KEY>"
}
}
}
What it does
StoryLenses MCP Server gives your AI agent the ability to write cover letters that actually work — not generic AI slop, but strategically structured narratives built on job analysis and profile matching. ## 5 Tools - storylenses_analyze_job — Extract 15+ structured fields from any job posting: requirements, company challenges, culture signals, recruiter priorities - storylenses_match_profile — Match a candidate's CV against job data. Returns fit score, matching skills, career gaps, and the strongest narrative angle - storylenses_generate_letter — Generate a story-driven cover letter using one of 15+ narrative archetypes (Golden Fleece, Problem-Solver, Fool Triumphant, and more) - storylenses_quality_check — Score a cover letter 0-100 across four pillars: HR intelligence, self-reflection, narrative craft, and honesty - storylenses_list_archetypes — List available narrative archetypes and tones so the agent or user can choose a style ## Quick Start Get a free API key at https://www.storylenses.app/developers (10 generations/month, no credit card). ## Pricing - Free: 10 generations/month - Developer: $29/month (200 generations) - Scale: $99/month (1,000 generations) Learn more: https://www.storylenses.app/mcpSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




