mcpField
F
Faradars Courses

Faradars Courses

Local
github.comScience & Education0Updated 3d ago

About Faradars Courses

An unofficial, read-only MCP server for AI agents that exposes Faradars’ public course catalog and magazine. It helps users research courses, compare options, and find learning materials without an account.

Key features

  1. 01Search courses and videos
  2. 02Read prices, discounts, and syllabi
  3. 03Compare courses and read reviews
  4. 04Browse instructors and learning paths
  5. 05Search and read magazine articles

Use cases

  1. 01Find free courses by topic
  2. 02Check a course’s price and syllabus
  3. 03Compare courses and instructor offerings
  4. 04Locate tutorials in Faradars Magazine

MCP support

Exposes 16 read-only tools to MCP clients over stdio for accessing public Faradars course, instructor, learning-path, offer, FAQ, and magazine data.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"sepehr071-faradars": {
"command": "uvx",
"args": [
"faradars-mcp"
],
"env": {
"FARADARS_MCP_PROXY": "<FARADARS_MCP_PROXY>"
}
}
}
}
Run commanduvx faradars-mcp
Environment variables to set
FARADARS_MCP_PROXYOptional HTTP proxy URL for the Faradars requests; system proxy settings are ignored. Also accepts a comma-separated list: one is used until it gets blocked or fails to connect, then the next.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypifaradars-mcp0.2.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

faradars-mcp: Faradars (فرادرس) course search MCP server for AI agents

faradars-mcp is an unofficial, read-only MCP server that gives AI agents the public course catalog of Faradars (فرادرس), the large Persian online learning platform.
Its 16 tools search courses and videos, read prices, discounts and syllabi, compare courses, list student reviews, browse categories and instructors,
walk learning paths, list offers and coupons, and search and read the Faradars Magazine (مجله فرادرس). No API key or Faradars account is needed.

PyPI Python License: MIT

For AI agents · Quick start · What it can do · Tools · فارسی


For AI agents

  • What: unofficial MCP server (model context protocol) for faradars.org: course and video search with filters, course details (price, current sale, duration, rating, students, instructors, objectives, syllabus), student reviews, category tree, instructor profiles, learning paths, related courses and comparison, discount campaigns and subscription plans, help answers, and Faradars Magazine article search and full text.
  • Install: uvx faradars-mcp or claude mcp add faradars -- uvx faradars-mcp. Transport: stdio. Needs uv (Python 3.10+).
  • Auth: none. Optional FARADARS_MCP_PROXY (HTTP proxy URL, or a comma-separated list); system proxy settings are ignored.
  • Access: read-only. It cannot log in, buy, enrol or comment, so no confirmation is needed before calling any tool.
  • Tools: 16, all prefixed fr_. Typical sequences: fr_search_courses -> fr_course -> fr_course_reviews; fr_course -> fr_related_courses -> fr_compare_courses; fr_instructors -> fr_instructor; fr_learning_paths -> fr_learning_path; fr_articles -> fr_article.
  • Use when: the user asks which Faradars courses exist on a topic, how much a course costs, whether it has a discount or certificate, what its syllabus is, who teaches it, which courses are free, or wants a tutorial from the Faradars Magazine.
  • Do not use when: the user wants to watch lessons, buy, or see their own account (not supported).
  • Output: compact JSON. Prices are Toman, durations hours, text is Persian as on the site.
  • Machine-readable: server.json.

What it can do

  • Search courses and videos by text, category, free or paid, length, certificate or instructor, sorted by sales, views, relevance or date
  • Read a course: price, active sale and its end time, hours, lesson count, rating, student count, objectives, prerequisites, description and the full syllabus
  • Read student reviews, 10 at a time
  • Browse the category tree, instructors and learning paths (مسیر یادگیری)
  • Search the magazine (blog.faradars.org) for tutorials and comparisons

Example prompts:

  • "Find the best-selling Python courses on Faradars and show me the syllabus of the first one."
  • "Which free Excel courses does Faradars have?"
  • "What else does the instructor of this course teach?"
  • بهترین دوره‌های آموزش پایتون در فرادرس کدام‌اند و قیمتشان چند است؟
  • دوره‌های رایگان اکسل با گواهینامه را پیدا کن.

Quick start

You need uv. No API key or account.

Claude Code
claude mcp add faradars -- uvx faradars-mcp
Claude Desktop, Cursor, Windsurf, Gemini CLI

Add to the client's MCP config:

{
  "mcpServers": {
    "faradars": { "command": "uvx", "args": ["faradars-mcp"] }
  }
}
VS Code (Copilot agent mode)
{
  "servers": {
    "faradars": { "type": "stdio", "command": "uvx", "args": ["faradars-mcp"] }
  }
}
Anything else

It is a standard stdio MCP server: run uvx faradars-mcp, or pip install faradars-mcp and run faradars-mcp.

Tools

ToolWhat it does
fr_search_coursesSearch courses, videos, exams, podcasts and webinars by text, category, price, length, certificate, instructor or trend
fr_courseGet one course: price and sale, duration, rating, students, instructors, prerequisites, objectives, syllabus, included extras
fr_course_reviewsGet student reviews (stars and comment) of a course, newest first
fr_related_coursesGet a course's related courses: same instructor, recommended next steps, similar topics
fr_compare_coursesCompare 2-4 courses side by side (price, sale, length, rating, students, certificate)
fr_categoriesList course categories as a tree of slugs and names
fr_suggestGet the site's search-box suggestions for the start of a phrase
fr_instructorsFind instructors by name, or the top instructors of a category
fr_instructorGet an instructor's profile, rating statistics and courses
fr_learning_pathsList or search curated learning paths (course collections)
fr_learning_pathGet one learning path: its ordered courses, totals and related paths
fr_offersList current discount campaigns, public coupon codes and subscription plans
fr_faqGet Faradars' general help answers (buying, access, certificates, support)
fr_articlesSearch Faradars Magazine articles by text, category or tag, or list the newest
fr_articleRead one Magazine article: key points, outline, text, views and rating
fr_article_topicsList Magazine categories or tags with article counts

All 16 tools are annotated readOnlyHint: true.

How it works

  AI agent  ──MCP over stdio──▶  faradars-mcp  ──HTTPS──▶  faradars.org/api/client      courses, categories, instructors
                                                  └──────▶  blog.faradars.org/wp-json    magazine

Requests look like Faradars' own web app (Chrome TLS fingerprint and headers), at most two at a time, with a 5 minute cache. Set FARADARS_MCP_PROXY=http://host:port to route through a proxy.

Notes

  • Unofficial. Not affiliated with or endorsed by Faradars. It reads the same public data the website shows to anyone.
  • Course content (videos) is not exposed; only catalog data.
  • Prices change with Faradars sales (sale_price is time-limited).

Development

uv sync
uv run ruff check . && uv run ruff format --check .
uv run python -m pytest -q          # offline
uv run python -m pytest -m live -q  # real faradars.org

فارسی

faradars-mcp یک سرور MCP غیررسمی و فقط‌خواندنی برای فرادرس است. با آن، دستیار هوش مصنوعی می‌تواند دوره‌ها را جست‌وجو کند، قیمت و تخفیف و سرفصل‌ها را بخواند، نظر دانشجویان را ببیند، مدرس‌ها و مسیرهای یادگیری را پیدا کند و در مجله فرادرس بگردد. نیازی به کلید API یا حساب کاربری نیست.

نصب: claude mcp add faradars -- uvx faradars-mcp

License

MIT. Built by Sepehr Radmard (سپهر رادمرد).

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.