原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Divar

作者:sepehr071版本 0.3.0i★ –i在你的电脑上运行
注册名称io.github.sepehr071/divar-mcp

安装

概览

作者提供的说明(英文原文)

Unofficial read-only Divar: search Iran's classified ads, cheapest and best-value ads, price checks.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 营销与社交媒体

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

你需要

  • PyPI已安装 Python 的 uv(用于 uvx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "divar": {
      "command": "uvx",
      "args": [
        "divar-mcp"
      ],
      "env": {
        "DIVAR_MCP_PROXY": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add divar --env DIVAR_MCP_PROXY=your-value -- uvx divar-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "divar": {
      "command": "uvx",
      "args": [
        "divar-mcp"
      ],
      "env": {
        "DIVAR_MCP_PROXY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "divar": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "divar-mcp"
      ],
      "env": {
        "DIVAR_MCP_PROXY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • DIVAR_MCP_PROXY env
    Optional HTTP proxy URL for requests to divar.ir, or a comma-separated list: one is used until it gets blocked or fails to connect, then the next. System proxy settings are ignored.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 sepehr071 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“营销与社交媒体”中的其他服务器比较i

  • 星标数多于此分类中其他 3589 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 3589 个服务器的 94% 更新
  • 基础检查结果等于或优于此分类中其他 3589 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Divar 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.3.0)于昨天进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它?

同一分类中有:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

MCP YouTube Transcript

作者:jkawamoto

An MCP server retrieving transcripts of YouTube videos

在你的电脑上运行★ 495MIT11天前更新
安装

Google Analytics MCP

作者:surendranb

GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.

在你的电脑上运行★ 244MIT11天前更新
安装

AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.

在云端运行★ 137MIT11天前更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

divar-mcp: Divar MCP server for AI agents

Let your AI agent search Divar (دیوار) ads in any Iranian city, and tell it whether a price is fair.

An unofficial, read-only MCP server for Divar, Iran's largest classifieds site (homes, cars, phones, jobs, services).

Search, read ads, compare, find the cheapest and best-value ads, appraise prices and browse the map from Claude, Cursor or Copilot. Prices are in Toman.

For AI agents · Why · What it can do · Quick start · Tools · How it works · Good to know · FAQ · Configuration · فارسی · Development


For AI agents

  • What: unofficial MCP server (model context protocol) for Divar (دیوار, divar.ir), Iran's classifieds site. Persian queries work best; Arabic letter variants (ي/ك) are folded.
  • Install: uvx divar-mcp or claude mcp add divar -- uvx divar-mcp. Transport: stdio. Needs uv (Python 3.10+).
  • Auth: none, no API key or account. Optional DIVAR_MCP_PROXY (HTTP proxy URL, or a comma-separated list); system proxy settings are ignored.
  • Access: read-only on Divar. It cannot log in, post, chat, bookmark or reveal a seller's phone number, so no confirmation is needed before calling a tool. Only dv_watch and dv_price_trend write, and only to a local file of your own searches.
  • Tools: 31, all prefixed dv_. Start with dv_search, dv_post, dv_cheapest, dv_best_for_budget, dv_market.
  • Typical sequence: dv_cities / dv_categories -> dv_filters -> dv_search -> dv_post -> dv_similar / dv_appraise / dv_compare.
  • Also: resources divar://cities, divar://categories, divar://category-filters/{slug}; prompts compare_ads, best_under_budget, appraise_listing, watch_market.
  • Units: prices in Toman (Divar's own unit, nothing is converted). price for a sale; deposit + rent for a rental (rent 0 with full_deposit means رهن کامل); no price means negotiable.
  • Use when: the user wants to find, price-check or monitor Divar ads (flats to buy or rent, used cars, phones, furniture, jobs...), or asks what something costs in a city.
  • Do not use when: the user wants to post an ad, message a seller or get a phone number (login-only on Divar), or needs a market other than Divar.
  • Output: compact JSON ad cards. Pass token between tools and next_cursor back as cursor.
  • Machine-readable: server.json and the iran-mcp catalog (TOOLS.md, servers.json, llms.txt).

Why

Divar is where Iranians buy and sell flats, cars and phones, but answering "what is a fair price for a 2-bedroom flat in Vanak?" means scrolling through dozens of ads and ignoring the fake prices. With divar-mcp an agent fetches the ads, drops placeholder prices, computes the median and quartiles of the asking prices, and tells you which ads are well below them.

You: Find the best 2-bedroom flat to rent in Vanak with a deposit under 1 billion Toman.

Agent: *calls* dv_parse_query -> dv_best_for_budget -> dv_post

It lists the best-value ads against the median of the ads that fit, with the reasons for each score, then opens the one you pick.

What it can do

  • Search ads in one or several cities by category, text, neighbourhood, price (and deposit for rentals), brand and model, photo, freshness and every other filter of the category; merge several pages with duplicates removed; continue with a cursor
  • Read a full ad: price in Toman, specs, features, description, all images, map position, seller type, placeholder-price detection
  • Find value: cheapest ads (junk prices skipped), best value and most-for-the-budget, ads priced well below the median, side-by-side comparison showing only the differences, similar ads
  • Judge a price: fair-price appraisal with percentile and confidence, market statistics by district and by day
  • Monitor: poll dv_new_since with the last timestamp to see only new ads; keep saved searches and a daily median price trend locally; export results as CSV or JSON lines
  • Use the map: ads around a GPS point or landmark with distances; neighbourhoods, neighbours, borders, address of a point
  • Look at sellers and dealers: how many ads a seller has, the business card and its ads

Example prompts:

  • "Cheapest used Peugeot 206 in Tehran, and is it priced fairly compared with similar ads?"
  • "Find apartments to rent near Vanak under 8 billion Toman and compare the top three."
  • "Show new iPhone 15 ads in Mashhad since this morning."
  • "What is the median price per square metre for apartments for sale in Gisha?"
  • ارزان‌ترین آپارتمان ۲ خوابه اجاره‌ای در ونک با ودیعه زیر ۱ میلیارد کدام است؟
  • قیمت این ماشین نسبت به آگهی‌های مشابه گران است یا ارزان؟
  • آگهی‌های جدید گوشی آیفون ۱۵ در مشهد را از امروز صبح نشان بده.

Quick start

You need uv. No API key or account.

Claude Code

claude mcp add divar -- uvx divar-mcp

Claude Desktop

Settings → Developer → Edit Config, then add:

{

"mcpServers": { "divar": { "command": "uvx", "args": ["divar-mcp"] } } }

</details>

Cursor

Add the Claude Desktop block above to ~/.cursor/mcp.json (or .cursor/mcp.json in a project).

VS Code (Copilot agent mode)

Click Install in VS Code above, or add to .vscode/mcp.json:

{

"servers": { "divar": { "type": "stdio", "command": "uvx", "args": ["divar-mcp"] } } }

</details>

Codex CLI

codex mcp add divar -- uvx divar-mcp

Or in ~/.codex/config.toml:

[mcp_servers.divar]

command = "uvx" args = ["divar-mcp"]

</details>

Gemini CLI

Add to ~/.gemini/settings.json:

{

"mcpServers": { "divar": { "command": "uvx", "args": ["divar-mcp"] } } }

</details>

Windsurf

Add the Claude Desktop block to ~/.codeium/windsurf/mcp_config.json.

Anything else

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

Tools

An ad card has token, title, price (sale) or deposit + rent (rent 0 with full_deposit means رهن کامل), info (mileage, condition...), district, seller (agency label), age_h (hours since the last bump), photos, image (thumbnail URL, only from dv_search with thumbnails), chat, tag (paid promotion), url, and suspect_price when the price looks like a placeholder. Absent flags mean false. Default page size is 10 to 20 ads.

All tools start with dv_ and are annotated read-only, except dv_watch and dv_price_trend, which write only to a local file.

Find places and categories
ToolWhat it does
dv_citiesCity ids for a name (1,177 cities); no query lists the biggest cities
dv_districtsNeighbourhoods of a city with ids, centre and main streets
dv_neighboursNeighbourhoods adjacent to a district (Divar's list plus the nearest ones by distance)
dv_locateCity, neighbourhood and street address of a GPS point
dv_place_searchMap autocomplete: landmark or street to coordinates
dv_place_mappingConvert old Divar place ids to current ones
dv_categoriesThe 236-node category tree; search by name, list children
dv_filtersEvery filter of a category: key, type, label, unit, options
dv_filter_optionsBrand and model keys (161 car brands), districts and other option lists, with typed search
dv_suggestThe search box's suggestions and category guesses for some text
dv_parse_queryA plain Persian request ("آپارتمان اجاره ونک زیر ۸ میلیارد") to dv_search arguments: city, neighbourhoods, price bounds, area (80 متری), category
dv_boundaryNeighbourhood borders of a city (GeoJSON): the city box, or one neighbourhood's polygon
Search and price
ToolWhat it does
dv_searchSearch ads with city, category, text, districts, price, brand, photo, freshness and any category filter; multi-page merge, client-side age and keyword filters, cursor paging
dv_countHow many ads match a search (capped at 10,000)
dv_cheapestThe cheapest ads of a search; placeholder prices and far-below-median outliers skipped
dv_best_for_budgetWithin a budget: best value with an explainable deal_score (and reasons) against the median of the ads that fit (price per m2 for property for sale), and the most you can get; bait / co-op / loan titles are skipped
dv_find_dealsAds priced well below the median of a search, no budget needed; junk prices and bait titles removed
dv_marketPrice statistics (min, quartiles, median, max) plus breakdown by district and by day
dv_appraiseIs an ad's price (or a price you give) high or low versus similar ads (same area first, then the whole city): percentile, verdict ("insufficient comparables" when the call is extreme but thin), confidence
dv_new_sinceAds published after a timestamp: poll with the returned latest to watch a search
dv_exportThe ads of a search as CSV or JSON lines
dv_nearbyMap ads around a point (category required), nearest first, with coordinates, distance and total price
dv_watchSaved searches: create, then check to get only the ads newer than the last check (local file)
dv_price_trendOne median asking price per day for a search, kept locally, with change since the previous day
dv_statusIs Divar reachable, latency, caches, saved watches and the tool list
One ad and its seller
ToolWhat it does
dv_postFull ad: price, specs, features, description, images, map position, seller type, flags
dv_postsUp to 10 ads in one call, compact
dv_compare2 to 6 ads side by side: prices and only the specs that differ
dv_similarAds like this one (same brand and area, widening step by step)
dv_sellerA seller's personal and business ad counts, business card (or "personal seller") and other ads (only business sellers' ads are listed, the first 11)
dv_dealerA business's public page: name, member since, first 11 ads

How it works

  AI agent  (Claude, Cursor, Copilot, ...)

│ │ MCP over stdio ▼ diva

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx