How to Connect Mercado Pago to Microsoft Copilot via MCP

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

Mercado Pago + Microsoft Copilot

Mercado Pago seller account (Argentina, Brazil, Mexico, Chile, Colombia, Peru, Uruguay): payments with fees, net amounts and release dates, merchant orders, subscriptions, payment methods, and the released money and account money reports for reconciliation (generate, list, download). Moves no money.

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:

MERCADO_PAGO_ACCESS_TOKEN

Step 1 — Get credentials

Setting up takes about 3 minutes. You need the Mercado Pago account whose data you want and an application in the Mercado Pago developers panel (any name will do).

1. Sign in at https://www.mercadopago.com/developers/panel/app with that account, open Your integrations and create an application if you have none. Any name works, and the product Checkout Pro or Payments is fine.
2. In the application, open Production credentials and activate them (accept the terms).
3. Copy the Access Token (it starts with APP_USR-) into MERCADO_PAGO_ACCESS_TOKEN, alone, without the word Bearer, spaces or quotes. The Public Key, Client ID and Client Secret are not needed.
4. Install the connector and run mercado_pago_get_account: it shows the account behind the token and its country site (MLA Argentina, MLB Brazil, MLM Mexico, MLC Chile, MCO Colombia, MPE Peru, MLU Uruguay).

The token opens the whole account: keep it secret, and if it leaks, reset it in the same panel and paste the new one. Test credentials only see test data, and the reports of test accounts are empty.

What it reads: the account; the payments of the last 12 months with status, gross amount, net received after fees, fee details, payment method and card brand, installments, payer, external reference and money release date; every detail of one payment, including refunds, items and shipping; the merchant orders of the last 90 days (the order behind a Checkout Pro or QR sale, with its payments and shipments); subscriptions with status, amount, frequency and next payment date; and the payment methods of the account's country with minimum and maximum amount and accreditation time.

Searching payments: the AI filters by status, by a date range on creation, approval, last update or money release date, and by your external reference. It gets 1 to 100 payments per page, sees how many match in total and pages through the rest. For a whole month of bookkeeping the reports are the better tool.

Reports for reconciliation: the released money report (Dinero liberado / Dinheiro liberado: the money that became available, with each payment, fee, refund and withdrawal) and the account money report (Dinero en cuenta, formerly all transactions: every movement of the balance). The AI first lists the reports that already exist, including the scheduled ones set up in the Mercado Pago panel. If none fits, it generates one for your period, waits until its status is processed (a minute or more) and downloads it. CSV reports arrive as semicolon-separated text with a header row and the columns configured in the panel; XLSX reports arrive as a file.

Amounts and dates: amounts are decimals in the account currency (ARS, BRL, MXN, CLP, COP, PEN or UYU). Payment dates carry the account's time zone offset, report dates are UTC: midnight in Buenos Aires is 03:00 UTC.

Asks before every change: mercado_pago_create_release_report and mercado_pago_create_settlement_report are the only tools that write. They create a report file on the account and change no money. The AI shows you the report type and period and waits for your yes. Everything else only reads.

Limits: payment search reaches back 12 months, merchant orders 90 days. Mercado Pago refuses a report end date in the future or beyond its own cut-off and names the latest allowed date. Report text over 200 KB is cut, so the AI uses shorter periods. After a 429 (local_rate_limited or too_many_requests) it waits a minute before trying again.

Common errors: 401 means a wrong, reset or test token. 403 means the token's application has no access to that resource. 404 on a payment means it belongs to another account.

The connector moves no money: it does not refund, pay out or charge, and it does not create payment preferences or payment links.

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 Mercado Pago 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

• "How much did we take in through Mercado Pago last week, and how much was left after fees?"
• "Find the payment with the external reference ORDER-1042 and tell me if it was refunded."
• "Which payments will be released to my balance in the next 7 days, and how much in total?"
• "Create the released money report for September and sum up the fees and refunds. Check with me before you generate it."
• "Which of our subscriptions are paused or cancelled, and what did each of them pay per month?"

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