HeyGen MCP server for AI agents

Live

API KEY

AI VIDEO

AI

HeyGen gives your agent AI video production: create avatar and template videos, translate and lip-sync videos, generate speech, images, and music, cut long videos into clips, and manage avatars, voices, and brand kits.

  • Per-user credentials: each call uses the actual user's API key, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
HeyGen
agent · Acme Q3
Run
Is the onboarding avatar video finished rendering?
S
heygen_get_video
107ms
Video agent
Yes. The onboarding video completed 6 minutes ago. It runs 2 minutes 14 seconds, and the video URL is ready.
Sources: 1 video
heygen
1 video
18:29
Message Claude...

Tools your video agent reaches for on HeyGen, scoped per user.

CALL ANY TOOL
107 tools for AI video in HeyGen: create avatar, template, and studio videos, translate, lip-sync, and proofread subtitles, generate speech, images, and music, clip long videos, and manage avatars, voices, assets, and brand kits.
heygen_clone_voice
Clone voice
Create a voice clone from an audio file. Returns voice_clone_id. Use to add a custom voice to the workspace. Provide the audio as a URL or an uploaded asset id. Poll get_voice until the clone is ready.
Parameters
Name
Type
Required
Description
audio
object
Required
Audio file for voice cloning. Provide as {type: 'url', url: '...'}, {type: 'asset_id', asset_id: '...'}, or {type: 'base64', media_type: '...', data: '...'}.
voice_name
string
Required
Display name for the cloned voice. Up to 100 characters; names longer than 64 characters are stored truncated to 64.
language
string
Optional
Language hint for the voice (e.g., 'en', 'es'). Auto-detected if omitted.
remove_background_noise
boolean
Optional
Remove background noise from the audio before cloning.
heygen_create_ai_clipping
Create ai clipping
heygen_create_background_removal
Create background removal
heygen_create_filler_word_removal
Create filler word removal
heygen_create_image
Create image
heygen_create_podcast
Create podcast
heygen_create_template_from_video
Create template from video
heygen_delete_ai_clipping
Delete ai clipping
heygen_delete_avatar_look
Delete avatar look
heygen_delete_lipsync
Delete lipsync
heygen_delete_template
Delete template
heygen_edit_video
Edit video
heygen_generate_speech
Generate speech
heygen_get_ai_clipping
Get ai clipping
heygen_get_background_removal
Get background removal
heygen_get_folder
Get folder
heygen_get_podcast
Get podcast
heygen_get_video_agent_resource
Get video agent resource
heygen_list_ai_clippings
List ai clippings
heygen_list_avatar_looks
List avatar looks
heygen_list_lipsyncs
List lipsyncs
heygen_list_templates
List templates
heygen_list_video_agent_styles
List video agent styles
heygen_search_assets
Search assets
heygen_send_video_agent_message
Send video agent message
heygen_set_template_variables
Set template variables
heygen_stop_video_agent_session
Stop video agent session
heygen_update_avatar_group
Update avatar group
heygen_update_brand_kit
Update brand kit
heygen_upload_proofread_srt
Upload proofread srt

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// HeyGen tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["heygen"], toolNames: [
    "heygen_list_avatar_looks",
    "heygen_create_avatar_video",
    "heygen_get_video"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Create an avatar video of our presenter reading the product update script" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["heygen"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Create an avatar video of our presenter reading the product update script" }],
  tools,
});

// Execute the tool call with the user's vaulted HeyGen API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["heygen"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Create an avatar video of our presenter reading the product update script" }],
  tools,
});

// Tool call runs with the user's vaulted HeyGen API key
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["heygen"] }, pageSize: 100,
});

const agent = new Agent({
  name: "video_agent",
  model: "gemini-2.5-pro",
  instruction: "HeyGen tools scoped to this user",
  tools,
});

await agent.run("Create an avatar video of our presenter reading the product update script");
Try these prompts
Copy any prompt into your agent. Each maps directly to a HeyGen tool. Click to copy, paste into your agent, done.
Videos
Copy the prompt
Copied
Create an avatar video of our presenter reading this product update script.
Copy the prompt
Copied
Generate a video from the weekly update template with this week's numbers.
Copy the prompt
Copied
Cut this webinar recording into short clips for social.
Localize and clean up
Copy the prompt
Copied
Translate the onboarding video into Spanish and French.
Copy the prompt
Copied
List the languages available for video translation.
Copy the prompt
Copied
Remove filler words from yesterday's recorded demo.
Avatars, voices, and brand
Copy the prompt
Copied
Find a warm, confident narrator voice.
Copy the prompt
Copied
Create a brand kit from our website.
Copy the prompt
Copied
List the avatar looks in our workspace.
SEE HOW AUTH WORKS
Each user connects their own HeyGen API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
HeyGen
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
HeyGen
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
HeyGen
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
HeyGen
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other AI and media connectors.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
Test other agents
See the same per-user auth pattern across other AI and media connectors.
SALES
Outbound prospecting agent
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared HeyGen API key looks fine in a demo. In production every video render looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
HeyGen today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access HeyGen as the user or through a shared API key?
As the user. Each user connects their own HeyGen API key once, and Scalekit sends it with every call. Audit logs attribute every video render and delete to that user, not a shared service account.
Where is the HeyGen API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in HeyGen?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example video creation and status without heygen_delete_video, which permanently deletes a video and its files, or heygen_delete_avatar_group. Scalekit also enforces scope checks before every API call.
What happens when a user revokes HeyGen access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
How does the agent know when a video is ready?
Video jobs run asynchronously. Creation tools return an id, and the matching get tool, such as heygen_get_video or heygen_get_video_translation, returns the status and the video URL once the job completes.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""heygen"": {
""url"": ""https://mcp.scalekit.com/heygen"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.heygen]
url = ""https://mcp.scalekit.com/heygen""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""heygen"": {
""url"": ""https://mcp.scalekit.com/heygen"",
""type"": ""http""
}
}
}