Connect HeyGen to Microsoft Copilot via MCP

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

HeyGen + Microsoft Copilot

Let your AI make HeyGen avatar videos with your own key: pick avatars and voices, turn a script or a prompt into a talking video, fill your templates, translate videos into other languages with lip-sync, create photo avatars, and check renders and your balance.

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:

HEYGEN_API_KEY

Step 1 — Get credentials

1. Sign in at https://app.heygen.com and open the API dashboard (https://app.heygen.com/developers/api).
2. Generate an API key and copy it. API usage is billed separately from a HeyGen web subscription: add balance or a payment method there if the account has none.
3. Paste the key into HEYGEN_API_KEY and install the connector. The key is sent only to HeyGen. A key restricted to some scopes needs read access to avatars, voices, videos, templates, translations and the user, and write access for the tools that create.
4. Start with heygen_get_account: it shows your billing type and what you have left to spend.

Billed to your HeyGen API balance: videos, translations and avatars are paid from your API balance (a pay-as-you-go wallet or your plan's credits). HeyGen bills video by length and engine; the current prices are in the API dashboard, and a refused call (402) says how much was needed. Listing and checking is free.

Confirm first: before heygen_create_video, heygen_generate_from_template, heygen_create_agent_video or heygen_translate_video, the AI tells you what will be made (avatar, voice, script length, format, languages, engine) and waits for your yes. heygen_create_photo_avatar only takes a photo of someone who agreed to it, such as yourself, and the AI asks you to confirm that you have that right. heygen_delete_video is switched off at install.

How a video is made:

1. The AI picks a character with heygen_list_avatar_groups and one of its looks with heygen_list_avatar_looks; the look is the presenter. A voice from heygen_list_voices is optional, otherwise the avatar's own voice speaks.
2. heygen_create_video takes the script (up to 5,000 characters), the format (for example 9:16 for shorts) and the engine, and returns a video id at once.
3. The video renders in the background. The AI checks heygen_get_video about every 30 seconds; a render takes from a minute to several minutes, longer for long scripts.
4. The finished video comes with an MP4 link, a captioned version, SRT subtitles and a link to the video in HeyGen. Download links expire; ask again for fresh ones.

Other ways to make a video:

• Templates: heygen_list_templates and heygen_get_template show your API-ready templates and their variables; heygen_generate_from_template fills every text variable and renders the video.
• Video Agent: heygen_create_agent_video turns a prompt into a whole video (script, scenes, avatar); heygen_get_agent_session follows it until the video renders.
• Translation: heygen_translate_video translates a video from a public link into one or more languages, with the speaker's cloned voice and lip-sync or as audio only; heygen_list_translation_languages lists the target languages.
• Photo avatar: heygen_create_photo_avatar makes a presenter from one portrait; heygen_get_avatar_look shows when it is ready to use.

Engines: avatar_iv is the default. avatar_v gives the most natural motion, but only for looks that support it. avatar_iii supports 4K for digital twins and studio avatars.

Limits: 10 videos, translations or agent sessions rendering at once on pay-as-you-go (more on Enterprise), 300 list calls and 500 status checks a minute. Source files must be public links: video up to 100 MB, audio up to 50 MB and 10 minutes.

Common errors: 401: the key is wrong or revoked. 402 insufficient_credit: the balance does not cover this video, and the message says how much is needed. usage_limit_reached or trial_limit_exceeded: a workspace or trial limit that an admin or a paid plan lifts. 403 insufficient_api_key_scope: the key is restricted; give it the scopes listed above. 400 invalid_parameter: the message names the field, for example an engine the look does not support. 404: an id that does not exist; the AI checks it with the list tools. 429: too many requests; wait and retry once later.

The connector uses HeyGen's API v3 (HeyGen retires the older v1 and v2 endpoints on 31 October 2026). It does not cover multi-scene studio videos, image-to-video, lip-sync of existing videos, voice cloning and voice design, text to speech on its own, interactive streaming avatars, file uploads (sources must be public links), proofreading translations, webhooks, brand kits, folders or batches.

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 HeyGen 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 is left on my HeyGen API balance?"
• "Show me my own avatars and which of their looks work best in 9:16."
• "Make a 45-second 9:16 video with my digital twin reading this script. Confirm the avatar, voice and length with me first, then send me the MP4 link when it is ready."
• "Fill our weekly update template with these three news items and render it."
• "Translate this product demo video into Spanish (Spain) and Japanese with lip-sync and tell me when both versions are ready."

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