Connect LINE to Microsoft Copilot via MCP

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

LINE Messaging API + Microsoft Copilot

Send push, reply and broadcast messages from a LINE Official Account, the main chat app in Japan, Taiwan and Thailand, and check the bot, its monthly message quota and user profiles. The free plan includes a monthly number of push messages (it varies by country); replies are free.

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:

LINE_CHANNEL_ACCESS_TOKEN

Step 1 — Get credentials

Setting up takes about 5 minutes. You need a LINE account to sign in to the LINE Developers Console; the LINE Official Account is created together with the channel.

1. Open the LINE Developers Console (developers.line.biz/console) and create a Provider.
2. Click Create a new channel and choose Messaging API. Set up the LINE Official Account that comes with the channel.
3. In the channel, open the Messaging API tab, scroll to Channel access token and click Issue to get a long-lived token.
4. Paste the token into LINE_CHANNEL_ACCESS_TOKEN.
5. Install the connector and run line_get_bot_info: it is free and shows the bot's basic id (@...), display name and chat mode, so you see that the token works and which account it belongs to.

The token is the account: it belongs to the channel, not to a person. Anyone who has it can post as your Official Account, so keep it secret.

What it reads: the bot itself (bot userId, basic id, display name, picture, chat mode and whether messages are marked as read automatically); the monthly push and broadcast limit with line_get_message_quota and how much of it was used this month with line_get_message_quota_consumption; the display name, profile picture, status message and language of a user who added the account as a friend; and, on verified and premium accounts, the userIds of your friends.

Who gets the message: LINE addresses people by userId, a U followed by 32 hex characters, never by display name. A userId comes from a webhook event, and this connector does not receive webhooks, so you give it to the AI. On verified and premium accounts the AI can also list your friends with line_list_follower_ids, up to 1000 per page; friends who blocked the account or did not agree to share their profile are left out. A push can also go to a group (C...) or a room (R...).

Monthly quota, free replies: the free plan includes a monthly number of push and broadcast messages, and that number depends on the country; paid plans raise it. line_get_message_quota shows your account's own limit. A broadcast goes to all your friends and counts once per friend, so one message to 2,000 friends uses 2,000 of the quota. Replies with line_reply_message are free and unlimited, but they need the replyToken of the user's message, which works once and expires about a minute later.

Asks before every send: line_push_message and line_broadcast_message reach real people. The AI checks how much quota is left, shows you the recipient and the exact message, and waits for your yes. With notificationDisabled a message arrives without a notification.

Switched off at install: nothing, all 8 tools are on. If the AI should never write to all your friends at once, an administrator can switch off line_broadcast_message.

Limits: one call sends up to 5 messages: text (up to 5000 characters), stickers, images, video, audio, locations, templates and flex messages. LINE accepts a broadcast right away and delivers it in the background, so the answer means LINE took the job, not that everyone has read it.

Common errors: "Invalid reply token" means the token was already used, has expired or was not a real one: send a push instead. "The value for the 'userId' parameter is invalid" means a display name or a made-up id was used instead of a real userId. A 403 on line_list_follower_ids means the account is not verified or premium.

The connector does not receive webhooks, so it does not read incoming messages or your chat history, and it cannot turn a display name into a userId.

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 LINE Messaging API 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 many push messages do we have left this month? Could we send one broadcast to all our friends without going over?"
• "Send U4af4980629f1b0c6d3e2a5b7c8d9e0f1 a message that the order is ready for pickup at our Shibuya store. Show me the text before it goes out."
• "Draft a broadcast for our autumn sale, 20% off this weekend only, and wait for my OK before it goes to everyone."
• "Which Official Account is this token connected to? Show me its @ id, display name and chat mode."
• "List our friends and tell me the display names and languages of the first 20."

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