avito-mcp-plugin
A plugin with skills and distributed MCP servers for parsing the Avito catalog, price monitoring and notifications, with an honest legal risk section
High risk
We rate an entry high when the tool writes to external systems, handles money, production databases or secrets, or runs arbitrary commands. The CLI installs it only with your consent.
Why this level
- Scraping public pages instead of the official API carries legal risk, as the README itself states
- Uses proxy rotation and works around the site's anti-bot protections
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/avito-mcp-pluginDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run one by one in the Claude Code chat
/plugin marketplace add evgenygurin/avito-mcp-plugin
/plugin install avito-mcp-plugin@avito-mcp-marketplaceInstall the plugin in Claude Code, Cursor, Codex or Gemini CLI per the AGENTS.md or GEMINI.md instructions in the repo, deploy the gateway plus scraper, db and notify roles per docs/architecture.md, set AVITO_SUPABASE_DSN for price history, then use the using-avito-mcp and scraping-avito skills.
This is third-party code. Review the repository files before installing.
What it does
The project does not go through the official Avito API; it scrapes public catalog listings: cookies, proxy rotation, and JSON extraction from the page. The architecture splits into roles: gateway is the single entry point with seven MCP tools (search_listings, get_listing, scan_new_listings, check_proxy_health, send_notification, export_listings, get_price_history) and MCP skill serving, scraper is the parsing engine itself, db stores price history and exports to Supabase, and notify sends Telegram and VK notifications. The using-avito-mcp and scraping-avito skills give an agent procedural knowledge of which tool to call when and how to work around anti-bot measures. The project deliberately does not implement getting a seller's phone number, to avoid collecting third parties' personal data beyond a listing's factual fields.
Who it is for. For people who want to track new listings and price history on Avito through an agent and are willing to accept the legal risks of scraping.
Good fit when
- You need to monitor new listings by set criteria with a Telegram or VK notification
- You need a listing's price change history, not just a current snapshot
- You are willing to use a clean Russian proxy, without which the network part cannot be verified
Not a fit when
- You are not willing to accept the legal risks of scraping public listings: the README explicitly warns about anti-bot measures, database rights and personal data
- You need an official, stable channel: this is page scraping, not a documented API
- You need a seller's phone number: the authors deliberately do not implement it
Example request
Find new bicycle listings in my city and notify me on Telegram if one appears under 15000Limitations
The README itself calls the status v0.5.0 and warns the network part cannot be verified without a clean Russian proxy: from an ordinary home IP, Avito returns 403 or 429 after two or three requests. There is a separate, explicit Disclaimer section on the legal risks of scraping in Russia: anti-bot measures, database rights, and personal data if you go beyond a listing's factual fields. The project gives no legal advice and explicitly places the risk on the operator.
How to disable. Remove the plugin from your agent and stop the deployed gateway, scraper, db and notify servers.
Security check
- Scraping public pages instead of the official API carries legal risk, as the README itself states
- Uses proxy rotation and works around the site's anti-bot protections
README in short
The README describes the v0.5.0 status and the goal of a full-featured Avito catalog parser, a gateway plus role-server architecture in a uv-workspace, a skills table, documentation sections on architecture, MCP servers, scraping and cross-agent portability, a project philosophy with an explicit refusal to collect a seller's phone number, and a separate section on the legal risks of scraping in Russia.
FAQ
Does this go through the official Avito API?
No, the project scrapes public catalog pages rather than using the documented seller API.
Can I get a seller's phone number from a listing?
No, the authors deliberately do not implement this, to avoid collecting third parties' personal data beyond the listing's own fields.
Related
An MCP server with n8n node and template knowledge: the agent picks nodes, validates configs and, with API access, creates workflows in your n8n
Zapier's official MCP plugin: the agent gets actions across thousands of apps through your Zapier account
Awesome Claude Skills by Composio
Awesome Claude Skills
A curated list of Claude skills and plugins, plus Composio's own automation skills for 78 SaaS apps
A plugin and CLI catalog for agents: generates command-line interfaces for GUI apps like GIMP and Blender and installs ready ones via CLI-Hub