How to Connect Avito to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Avito, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Avito + Microsoft Copilot

Let your AI work with your Avito business account: list your ads and change their prices, read views, contacts and calls statistics, check autoload uploads and their errors, the feed format and your wallet, and read Avito Messenger chats. Sending messages and changing autoload settings are optional and off by default.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

AVITO_CLIENT_ID, AVITO_CLIENT_SECRET

Step 1 — Get credentials

Setting up takes about 5 minutes and needs an Avito business account with its API credentials. There is no browser sign-in.

1. Sign in to Avito with the business account the AI should work with: the main company account, not an employee's.
2. Open Для профессионалов, then API интеграции (avito.ru/professionals/api), and copy Client ID and Client secret. Avito issues one pair per account, and generating a new secret makes the old one stop working.
3. Paste them into AVITO_CLIENT_ID and AVITO_CLIENT_SECRET and install. AnythingMCP gets the access token from Avito by itself and renews it every 24 hours.
4. Run avito_get_self: it shows the account's name, email and user id. That id is the user_id the other tools need, and the AI reuses it for the whole conversation.

What you get depends on your Avito tariff: the API can do what the account itself may do. The Messenger API comes only with the Максимальный tariff for goods and jobs, and with Расширенный or Максимальный for services; without it the chat tools answer 403. The autoload tools need autoload set up in the account.

What it reads: the account and its wallet (real money and bonuses, in rubles) with the charges for listings and promotion; your ads with title, price, status, category, address and the paid services applied (vip, highlight, pushup, premium, xl) with their end dates; unique views, contacts and favourites of up to 200 ads at once and up to 270 days back; calls per ad and per day; the autoload settings, every upload and the errors and warnings of each ad in it; the feed fields of every category; and your Avito Messenger chats and messages. Ads of employee sub-accounts are not listed, and reading a chat does not mark it as read.

Two ids per ad: the Avito id is the number in the ad's URL, and an ad that comes from an autoload feed also has the feed's own Id. The AI translates between the two, so you can ask about an ad by either one.

Asks before every change: avito_update_item_price changes the price of one ad, in whole rubles (goods, spare parts, cars and real estate, not short-term rentals). The new price is public at once, so the AI first tells you the ad, the old price and the new one and waits for your yes. If the ad comes from an autoload feed, the next upload can bring back the feed's price: change it in the feed too.

Switched off at install: avito_send_message (it writes to a buyer in the account's name, at most 1,000 characters, and cannot be unsent here), avito_mark_chat_read (the unread badge disappears, so colleagues may miss the message), avito_update_autoload_profile (it replaces the whole autoload profile) and avito_start_autoload_upload (it publishes every ad of the feed at once, ignoring the limits of the schedule, which can cost listing fees, and runs once an hour at most). An administrator turns them on deliberately, and even then the AI shows you the exact text or settings change and waits for your confirmation.

Buyers' data: chats contain buyers' names and messages. The AI uses them only to serve those buyers and never writes to people who did not write first.

Times and language: Avito works in Moscow time (UTC+3), and the AI converts times before quoting them. Avito's own messages are in Russian; the AI translates them when you work in another language.

Limits: listing ads at most 25 requests a minute, price changes 150 a minute, reading one ad 500 a minute. The wallet history covers at most one week per call and one year back. After a 429 the AI waits a minute before trying again.

Common errors: 401 Bad bearer token or 403 invalid access token means the Client ID or secret is wrong, or a newly generated secret replaced it. Any other 403 means the tariff does not include that API (Messenger above all). 404 means the ad, chat or upload does not exist or belongs to another account; the autoload reports also answer 404 while there is no upload yet. 400 means a parameter is wrong, for example a price in a category where it cannot be changed here, or a wallet window longer than a week.

The connector does not cover promotion services and their prices, ad campaigns, CPA and call tracking, delivery and orders, ratings and reviews, Avito Jobs, short-term rentals, employee accounts, webhooks, or sending images and voice messages, and it does not create or edit ad content: that goes through your autoload feed.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Avito tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "Which of my active ads got the most views and contacts in the last 30 days, and which got none at all?"
• "Lower the price of my ad iPhone 13 128 GB to 42,000 rubles. Show me the old and the new price first."
• "Did the last autoload upload have errors? List the ads with errors and tell me what to fix in the feed."
• "Which Avito Messenger chats are unread, and what are the buyers asking about?"
• "How much was charged to my Avito wallet last week and for what, and what is the balance now?"

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse