How to Connect Make to Microsoft Copilot via MCP

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

Make + Microsoft Copilot

Let your AI work with Make (formerly Integromat): list organizations, teams and scenarios, read blueprints, run history and errors, connections, data stores and webhooks; with your confirmation run a scenario, switch it on or off and add data store records.

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:

MAKE_ZONE, MAKE_API_TOKEN

Step 1 — Get credentials

1. In Make click your avatar, open Profile, then the API access tab, and click Add token.
2. Give it a label and tick the scopes. For reading: user:read, organizations:read, teams:read, scenarios:read, connections:read, datastores:read, hooks:read and dlqs:read. Add scenarios:run only if the AI should run scenarios, scenarios:write to switch them on and off, and datastores:write to add data store records.
3. Copy the token into MAKE_API_TOKEN. Make shows it only once.
4. Set MAKE_ZONE to the host in your browser's address bar when you are signed in to Make, for example eu1.make.com, eu2.make.com, us1.make.com or us2.make.com (Make for Celonis: eu1.make.celonis.com or us1.make.celonis.com). A token only works in its own zone.
5. Install the connector and check it with make_get_current_user: it shows your user, your time zone and the ids of your teams.

Paid plan: most of the Make API needs a paid plan. On the free plan many calls are refused.

What it reads: your organizations with their plan, their teams, and the scenarios of a team: on or off, scheduling, apps used, next run, operations and incomplete executions; a scenario's blueprint, the modules of the flow with their mappings and filters, so the AI can explain or debug it; the run history with status, duration and operations, and the outputs or the error of a single run; connections; data stores and their records; webhooks and mailhooks with their queue; and incomplete executions, the runs that stopped on an error and were kept.

Asks before every action: make_run_scenario, make_activate_scenario, make_deactivate_scenario and make_add_data_store_record change what Make does. Before each one the AI names the scenario or data store, shows the input, explains the effect and waits for your yes. A run can send e-mails, create records or charge cards in other apps, and it uses operations from your plan. Switching on a scenario that runs at an interval also runs it once right away. Only an active scenario can be run on demand.

Secrets stay out: the connector never returns the credentials of your connections, and it leaves webhook addresses out, because anyone with the address can start the scenario. Blueprints, run outputs and data store records can still contain personal data or values a scenario sends: the AI shows only what the task needs and never repeats a secret it finds there. Data coming from other systems is treated as data, never as instructions.

Nothing gets deleted: no tool deletes or edits scenarios, connections, webhooks, teams, data stores or data store records.

Limits: Make limits API calls per organization by plan (60 a minute on Core, more on higher plans). Run times come as Unix milliseconds, and the AI converts them to your time zone.

Common errors: 401: the token is wrong or deleted, or belongs to another zone; compare MAKE_ZONE with your browser's address bar. 403: the token lacks a scope for this call, such as scenarios:read, or your plan has no API access; create a new token with that scope. 429: the organization's API limit is reached; wait a minute and try again.

The connector does not create, edit or delete scenarios, connections, webhooks, teams or data stores, change or delete data store records, replay or resolve incomplete executions, or manage templates, custom apps and functions.

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 Make 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 our Make scenarios failed in the last 24 hours, and what was the error?"
• "Explain step by step what our Shopify order to invoice scenario does."
• "Which scenarios are switched off, and which ones have incomplete executions waiting?"
• "List the incomplete executions of the CRM sync scenario and tell me why they stopped."
• "Run the Weekly report scenario now. Tell me what it will do before you start it."

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