mcpField
K
Karnameh Cars

Karnameh Cars

Local
github.comBusiness & Marketing2Updated 4d ago

About Karnameh Cars

Karnameh Cars is an unofficial, read-only MCP server for AI agents accessing public data from Iran's Karnameh car marketplace. It combines used-car listings with new-car prices, specifications, comparisons, and magazine articles.

Key features

  1. 01Filter and read used-car ads
  2. 02Browse new-car prices and history
  3. 03Look up specs and compare variants
  4. 04View used-ad counts by city
  5. 05Search and read car magazine articles

Use cases

  1. 01Find used cars by brand, city, price, or mileage
  2. 02Check new-car prices and recent changes
  3. 03Compare vehicle specifications and reviews

MCP support

Exposes Karnameh's public used-car ads, price data, vehicle specifications, and magazine content as tools for MCP clients. It is read-only and requires no API key or account.

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-karnameh": {
"command": "uvx",
"args": [
"karnameh-mcp"
],
"env": {
"KARNAMEH_MCP_PROXY": "<KARNAMEH_MCP_PROXY>"
}
}
}
}
Run commanduvx karnameh-mcp
Environment variables to set
KARNAMEH_MCP_PROXYOptional HTTP proxy URL for the Karnameh 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
pypikarnameh-mcp0.1.1

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

karnameh-mcp: Karnameh (کارنامه) used-car ads and car prices MCP server for AI agents

karnameh-mcp is an unofficial, read-only MCP server that gives AI agents the public data of Karnameh (karnameh.com), an Iranian car marketplace.
Its 15 tools search used-car ads with real filters, read an ad in full, look up brands and cities, list today's market prices of new cars with history and biggest movers, give car specs and expert review summaries with side-by-side comparison, count ads per city, and read the Karnameh car magazine.
No API key or Karnameh account is needed. It works in Claude, Cursor, Copilot and any other MCP client.

PyPI Python License: MIT

For AI agents · Quick start · Tools · FAQ · فارسی


For AI agents

  • What: unofficial MCP server (model context protocol) for karnameh.com: used-car ads with filters (brand, model, city, price, year, mileage, inspected, instalments), full ad details, brand and city lookup, zero-km market prices and daily price history.
  • Install: uvx karnameh-mcp or claude mcp add karnameh -- uvx karnameh-mcp. Transport: stdio. Needs uv (Python 3.10+).
  • Auth: none, no API key or account. Optional KARNAMEH_MCP_PROXY (HTTP proxy URL, or a comma-separated list); system proxy settings are ignored.
  • Access: read-only. It cannot log in, contact sellers, book inspections or post ads, so no confirmation is needed before calling any tool.
  • Tools: 15, all prefixed kn_. Typical sequences: kn_cars -> kn_car; kn_price_list -> kn_price_history; kn_brands -> kn_cars; kn_specs_search -> kn_specs / kn_compare_specs; kn_articles -> kn_article.
  • Use when: the user asks what a used car costs in Iran, wants to find a car for sale by brand, model, budget or city, wants one ad read in full, or asks the price of a new (zero-km) car and how it moved lately.
  • Do not use when: the user needs the full Karnameh inspection report, a price estimate for their own car (both need a Karnameh login) or ads from other sites.
  • Output: compact JSON. Prices are Toman. Names and descriptions are Persian, as Karnameh has them.
  • Machine-readable: server.json and the iran-mcp catalog.

Quick start

claude mcp add karnameh -- uvx karnameh-mcp

Any other client: command uvx, args ["karnameh-mcp"].

Tools

ToolWhat it does
kn_carsSearch used-car ads by text, brand, model, city, price, year, mileage, inspected, instalments; sort; page.
kn_carOne ad in full: specs, description, strengths, inspection date, link and verdict.
kn_brandsBrand and model names in Persian and English.
kn_citiesCity slugs for kn_cars.
kn_price_listToday's market prices of new cars by brand, model, origin, country, price, year.
kn_latest_pricesMost recent price quotes with percent change.
kn_price_historyDaily average price per production year, plus each source's quote for a year.
kn_price_moversNew-car variants ranked by their latest percent price change (rises, drops).
kn_specs_searchFind a car variant's slug in the specs catalog.
kn_specsTechnical specs, AI review score, pros and cons, web reviews of one variant.
kn_compare_specsTwo to four variants side by side (only the differing rows by default).
kn_city_statsUsed-ad count and cheapest ad in every city, optionally per brand or model.
kn_inspection_centersKarnameh walk-in inspection and paint-check centers of a city.
kn_articlesSearch or list the Karnameh car magazine (news, reviews, maintenance, laws).
kn_articleOne magazine article as plain text.

FAQ

Does it need a Karnameh account? No. Everything is public data the website shows to anyone.

How many ads are there? Karnameh lists a few hundred used cars at a time, so this is not the whole Iranian market.

Why is there no price estimator or inspection report? Both need a Karnameh login on the website.

Proxy? The server ignores system proxies. Set KARNAMEH_MCP_PROXY if you need one.

فارسی

سرور MCP غیررسمی و فقط‌خواندنی برای کارنامه (karnameh.com): جستجوی آگهی خودروی کارکرده با فیلتر برند، مدل، شهر، قیمت، سال و کارکرد، خواندن کامل یک آگهی، قیمت روز خودروی صفر و روند قیمت. بدون کلید API و بدون حساب کاربری.

نصب: claude mcp add karnameh -- uvx karnameh-mcp

ساخته‌شده توسط سپهر رادمرد: github.com/sepehr071 · linkedin.com/in/sepehr-radmard

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.