HeyGen x Granola
Granola captures everything said in your meetings. HeyGen turns it into a lifelike video with avatar and voice. Connected through Claude via MCP, a single prompt is all it takes to go from call notes to a finished, narrated video.
Granola understands the context, HeyGen creates the video
When you type a prompt referencing a Granola meeting and a HeyGen video in the same sentence, Claude identifies the tools it needs and calls them in sequence, first reading your meeting history from Granola, and then generating the video through HeyGen.
Claude calls list_meetings to find the right call by name, date, or attendee, then get_meetings to pull the complete notes. It writes a video-length script from that content, then passes it to create_video_agent. The agent takes care of the rest, and you receive a video in your HeyGen library once rendering is complete.
“Pull my latest Granola meeting and turn it into a 60-second HeyGen video that I can share in Slack for the people who were not there.”
Connect Granola in Claude Connectors
In Claude, go to the top-left menu → Customise → Connectors. Click +, then Browse connectors, search for Granola, and click +. A sign-in page will open — log in to your Granola account to grant Claude authorisation access. For Claude Code, run: claude mcp add granola --transport http https://mcp.granola.ai/mcp
Add HeyGen as a custom connector
Go to developers.heygen.com/mcp/overview and copy the MCP endpoint URL. Back in Claude Connectors, click + → Add custom connector, name it HeyGen, and paste the endpoint: https://mcp.heygen.com/mcp/v1/
Ensure both connectors are switched on
Before starting a conversation, please confirm that both the Granola and HeyGen connectors are toggled on in your active Claude session. Both must be enabled at the same time for Claude to call them within the same workflow. You can check which tools are available by asking Claude: What MCP tools do you have access to?
Run your first prompt and copy the session URL
Try the action-item prompt from above, or start with: Pull my latest Granola meeting and turn it into a 60-second HeyGen video that I can share in Slack.
How three systems connect in a single prompt
Claude acts as the orchestrator, reading from Granola, reasoning about the content, and writing to HeyGen. Neither tool knows that the other exists. Claude is the bridge.
Granola adds the flavour notes
Makes meeting history available as tools you can query. Claude reads notes, transcripts, and attendee details from here.
Claude reviews the context
Orchestrates both MCPs, summarises the notes into a script, and calls HeyGen to produce the video.
HeyGen creates the video
Receives the prompt and renders a video. Returns the status and video ID once complete.
The tools Claude actually uses
Every tool listed here is real, taken from the published MCP documentation for both Granola and HeyGen. Claude chooses and arranges them according to what your prompt asks for.
list_meetings
Scan your meeting list by title, date, or attendees. Returns the meeting ID, title, date, and participants. On paid plans, it also includes notes shared with you and can be filtered by folder.
get_meetings
Fetch full meeting content by ID — private notes, AI-enhanced notes, attendees. This is the tool that pulls the actual meeting content Claude uses to write a video script.
query_granola_meetings
Chat directly with your Granola notes. Useful for open-ended questions like "what did we decide about pricing across all my calls last month?"
get_meeting_transcript
Zoom into the raw transcript with speaker identification. Useful when you want exact quotes in your video script rather than AI-summarised notes.
create_video_agent
One-shot video generation from a prompt. The agent manages scripting, avatar selection, scene composition, and rendering automatically.
get_video_agent_session
Poll the status, progress, and video_id for an active agent session. Claude calls this after create_video_agent to know when the video is ready and to retrieve the download URL.
create_video_from_avatar
Explicit video creation using a specific avatar ID, voice ID, and text script. Use this instead of create_video_agent when you want direct control over the avatar’s appearance and voice selection.
design_voice
Find voices that match a natural language description. Returns up to 3 matches. Useful for prompts that do not refer to a specific voice.
Create video translation
Translate a generated video into one or more target languages with voice cloning and lip-sync. Chain this after create_video_agent to produce multilingual recap videos.
Turning meetings into forward momentum
The goal is not just a summary video. It is a video that prompts the necessary stakeholders to engage and act on time, including those who were not on the call.
Meeting action points
The core workflow: pull the latest meeting, generate a 60-second video that opens with the outcome, walks through each decision, calls out every owner by name with their task and deadline, and ends with one clear request. Share it in Slack.
Stakeholder briefings
Pull notes from a strategy, launch, or leadership meeting and generate a narrated video for the people who need to act but were not present. Not a generic summary, but a direct call-out of what they need to know and do.
Launch and project decisions
When a launch strategy, project direction, or key decision gets finalised in a meeting, generate a video that clearly communicates the decision. Who owns which part of the launch, what is locked in, and what still needs input, and by when.
Accountability across meetings
Use query_granola_meetings to surface action items that are still open across multiple calls, then generate a video that clearly names each pending owner and each pending task.
Multilingual meeting summaries
Generate the action-item video from Granola notes in English, then chain create_video_translation for international versions — same callouts, in their language, lip-synced — all from a single Claude prompt.
Start creating videos with AI
See how businesses like yours scale up content creation and drive growth with the most innovative AI video.
