How to Connect Medmis to Microsoft Copilot via MCP

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

Medmis + Microsoft Copilot

Medmis clinic management platform (Russia): branches, specialists and schedules, appointments, patients, invoices, payments, price list, stock, to-do tasks and occupational check-ups. Booking or changing an appointment and creating a task are included, installed switched off; nothing is deleted.

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:

MEDMIS_URL, MEDMIS_LOGIN, MEDMIS_PASSWORD, MEDMIS_SYSTEM_NAME

Step 1 — Get credentials

Setting up takes about 5 minutes. You need a Medmis clinic account and an API user from Medmis support or your Medmis administrator.

1. Ask Medmis support ([email protected], with the subject marked DEV / API_CORE) or your Medmis administrator for an API user: a login, its password and the system name used to sign in. The API user's permissions decide what the tools can read (appointments.get, patients.get, patient_invoices.get, payments.get, schedules.get, stores.get, todo.tasks.get, profex.* and so on).
2. Set MEDMIS_URL to the address of your clinic's Medmis node, e.g. https://node3.medmis.ru, without /apix. Its API reference is at <MEDMIS_URL>/apix/swagger.
3. Fill in MEDMIS_LOGIN, MEDMIS_PASSWORD (at least 6 characters) and MEDMIS_SYSTEM_NAME.
4. Install the connector and run medmis_list_branches to check the access.

The connector signs in with POST /apix/v1/Auth/login and sends the access token as a Bearer header. Tokens last about an hour and are renewed automatically.

What it reads: the clinic's branches with address, contacts, working hours, licence and UTC offset; specialists with their specializations and branches, and the services each one can provide; the schedule grid of specialists for one or more branches and a date range, optionally only the free slots; appointments with UTC and local times, status, patient, specialist, source, visit type, cabinet and tags, plus their reference lists (statuses, types, visitations, sources, tags); patients by name, phone, e-mail, card number, birth date or age, sex, tags and more, and one patient's full record; patient invoices and their lines, and payments with their amounts per payment method; the price list (service categories and services); reserves (time held in a specialist's schedule); stores, the store nomenclature, stock levels and batches with expiry; internal to-do tasks; and the occupational check-up module (Профосмотры): companies, contracts and the people under them.

Switched off at install: medmis_create_appointment (book a free slot), medmis_update_appointment (move an appointment, cancel or confirm it through its status, change comment or tags) and medmis_create_task. They change the clinic's live schedule, so an administrator turns them on deliberately. Even then the AI shows you the patient, specialist, day and time and waits for your yes. Nothing is ever deleted through this connector.

Patient data: patients, appointments, invoices and payments are personal health data. The AI reads only what the question needs and does not repeat identity documents or contact data unless you ask. The patient list leaves out identity document numbers, INN and SNILS.

Dates and ids: day filters are YYYY-MM-DD; change-time filters are yyyy-MM-ddTHH:mm:ss in UTC. Appointments carry both UTC and local times (datetimeFromLocal) plus utcOffsetMinutes, and the AI quotes the local time. Branches, specialists, patients, appointments and payments use UUIDs; invoices, stores, materials, tasks and check-up records use numbers.

Limits: lists return items with totalCount and totalPages, at most 100 per page, starting at page 1. Medmis limits each method: filtered lists 20 requests a minute, reference lists 40, single records 100 and sign-in 40 a minute. A 429 means wait.

Common errors: 401 means a wrong login, password or system name, or an expired session (the connector signs in again once). 403 means the API user lacks the permission for that method. 400 ValidationError lists the bad fields, e.g. a password shorter than 6 characters or a malformed date. 404 means the id does not exist on your node.

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 Medmis 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 specialists have free slots at our main branch tomorrow afternoon?"
• "List today's appointments of the cardiologists with their status and local start times."
• "How much did we invoice last week per branch, and which invoices are still unpaid?"
• "Which store materials have expired batches, and how much of each is still in stock?"
• "Show the check-up contracts created this month and how many people are under each one."

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