aparat-mcp: Aparat (آپارات) Iranian video platform MCP server for AI agents
aparat-mcp is an unofficial, read-only MCP server that lets an AI agent search videos and channels, read video details and comments, and see what is trending on Aparat (آپارات, aparat.com), the biggest Iranian video platform.
Its 8 tools search videos and channels, show a video (views, likes, duration, tags, category, channel, publish date), its comments and related videos, show a channel and its newest or most viewed videos, and list trending videos overall or per category.
No API key or account is needed; it works in Claude, Cursor, Copilot and any other MCP client.
For AI agents · Quick start · Tools · Limits · فارسی
For AI agents
- What: unofficial MCP server (model context protocol) for aparat.com: video and channel search, video details, comments, related videos, channel pages and trending feeds.
- Install:
uvx aparat-mcporclaude mcp add aparat -- uvx aparat-mcp. Transport: stdio. Needs uv (Python 3.10+). - Auth: none. Optional
APARAT_MCP_PROXY(HTTP proxy URL, or a comma-separated list); system proxy settings are ignored. - Access: read-only. It cannot log in, upload, comment, like or follow. Video files and stream links are not exposed, only page URLs.
- Tools: 8, all prefixed
apr_. Typical sequences:apr_search->apr_video/apr_channel;apr_channel->apr_channel_videos;apr_categories->apr_trending;apr_video->apr_comments/apr_related. - Use when: the user asks what is popular on Aparat, wants to find Persian videos or a creator's channel, asks how many views, likes or followers something has, or wants to read what viewers say under a video.
- Output: compact JSON. Views are counts, duration is seconds, dates are Gregorian. Titles and comments are Persian.
Quick start
You need uv. No API key or account.
Claude Code:
claude mcp add aparat -- uvx aparat-mcp
Claude Desktop, Cursor, VS Code and other clients:
{
"mcpServers": {
"aparat": { "command": "uvx", "args": ["aparat-mcp"] }
}
}
Example prompts:
- "Search Aparat for Persian cooking videos."
- "What are the most viewed videos of the channel macharta?"
- "What is trending in music on Aparat?"
- نظرات این ویدیوی آپارات را بخوان.
- پربازدیدترین ویدیوهای کانال ماچارتا کداماند؟
Real answer (17 Nov 2026): apr_channel_videos(channel="macharta", sort="top") returned 2,118,476 views for the top video of that channel, then 1,650,691 and 1,488,902.
Tools
| Tool | What it returns |
|---|---|
apr_search |
Videos and channels matching a text, in relevance order, paged with next |
apr_video |
One video: title, description, views, likes, comments, duration, tags, category, channel, publish date |
apr_comments |
Top comments of a video, 10 per page |
apr_related |
Videos Aparat recommends next to a video (about 10) |
apr_channel |
A channel: name, followers, video count, total views, description, start date |
apr_channel_videos |
A channel's videos, newest first or most viewed, 10 per page |
apr_categories |
The category names Aparat's trending tabs use |
apr_trending |
Trending videos overall or in one category (up to 40) |
Limits
- Counters on Aparat change by the second, so a view count read twice a minute apart can differ slightly.
- Channel video lists and comments come 10 per page; search about 40 per page. Use the
nexttoken orpagefor more. - Overall trending (the site's "hottest" row) is not shown on Aparat's logged-out home page, so it was checked against the API only, not against the rendered page. Category trending was checked against the page.
- Stream links, downloads, live streams and anything behind a login (history, subscriptions, uploads) are not covered.
- Aparat answers both Iranian and foreign networks in testing; if your network is blocked, set
APARAT_MCP_PROXY. The server ignores system proxy variables on purpose.
How it works
Aparat has no public API documentation. The endpoints were mapped by watching aparat.com in Chrome, and every tool was then checked in Chrome against the real rendered pages (search, video, comments, channel, channel videos, categories, trending, related) on 16 Nov 2026. The server calls those same public endpoints through a Chrome-impersonating HTTP client, with a short cache and at most two requests at a time.
فارسی
aparat-mcp یک سرور MCP غیررسمی و فقطخواندنی برای آپارات (aparat.com) است. با آن یک عامل هوش مصنوعی میتواند ویدیوها و کانالها را جستوجو کند، جزئیات ویدیو (بازدید، لایک، مدت، برچسبها، دستهبندی)، نظرات و ویدیوهای مرتبط را بخواند، کانال و پربازدیدترین ویدیوهایش را ببیند و ویدیوهای پربازدید و داغ هر دسته را فهرست کند. بدون حساب کاربری و کلید API کار میکند. نصب در Claude Code:
claude mcp add aparat -- uvx aparat-mcp
Development
uv sync
uv run ruff check . && uv run ruff format --check .
uv run python -m pytest -q # offline tests on recorded fixtures
uv run python -m pytest -m live -q # live calls to aparat.com
Releases: bump the version in pyproject.toml and server.json, run uv lock, then push a v* tag; GitHub Actions publishes to PyPI.
Disclaimer
Unofficial and not affiliated with or endorsed by Aparat. It is read-only and uses the public pages and API of aparat.com, which can change without notice.
Author
Built and maintained by Sepehr Radmard (سپهر رادمرد). LinkedIn · GitHub · more servers in iran-mcp.
مجوز استفاده (License)
استفادهٔ شخصی و غیرتجاری رایگان است. استفاده در شرکت، محصول پولی یا پروژهٔ مشتری به مجوز تجاری نیاز دارد؛ از راه لینکدین یا گیتهاب با سپهر رادمرد تماس بگیرید. متن کامل: PolyForm Noncommercial 1.0.0. نسخههای پیش از 0.1.1 با مجوز MIT منتشر شدهاند و همان مجوز را دارند.
Free for personal and non-commercial use under the PolyForm Noncommercial License 1.0.0. Using it in a company, a paid product or a client project needs a commercial license: contact Sepehr Radmard on LinkedIn or GitHub. Versions before 0.1.1 were released under MIT and stay under it.
Metadata
Release files for aparat-mcp 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| aparat_mcp-0.1.1.tar.gz | 778.5 kB | With provenance | Details for aparat_mcp-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| aparat_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for aparat_mcp-0.1.1-py3-none-any.whl |
Total release size: 795.6 kB
Release files / aparat_mcp-0.1.1.tar.gz
| Download URL | aparat_mcp-0.1.1.tar.gz |
|---|---|
| Size | 778.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fa4b50303ba8fa63116ae751e306a138d3badd5be1a0bfa0f44d1191efa2e6de
|
|
BLAKE2b-256 checksum How to use checksums |
8a66413e6d0df6c96d646e60a9e3c8ef18be0ee1525b4034cbc10e67ef1a1845
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 17, 2026.
Transparency logRelease files / aparat_mcp-0.1.1-py3-none-any.whl
| Download URL | aparat_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 17.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
cdce9bb6d06aa680f05ae7f609e89dcfd576ca1a22b54a0c77a97263c71beb0b
|
|
BLAKE2b-256 checksum How to use checksums |
da4dfcc74a83907e5f092b142028526c9d3be783c20be3d3e27ec6198ff1812c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 17, 2026.
Transparency logSecurity for aparat-mcp 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for aparat_mcp-0.1.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 17, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.