Draft Sales Follow-Up Emails from Meeting Notes Automatically with SuperIntern MCP and Gmail
Everyone in sales knows the follow-up email works best when it lands fast. It is also the task that slips latest into the evening.
The call ends, the next meeting starts, and it's 6 PM before you reopen your notes and reconstruct what happened: the thank-you line, the bullet list of what was agreed, the homework on your side, the ask for the next meeting. By the time you hit send, the momentum from the call is gone. Your meeting lives in SuperIntern, your email lives in Gmail, and a human has always been the glue in between, working from memory.
This guide shows how to connect SuperIntern's MCP and Gmail to Claude, so that going from meeting notes to a ready-to-review follow-up draft takes exactly one prompt. The draft lands in your Gmail drafts folder; your job is to read it, tweak it if you want, and press send.
⚠️ This article was independently compiled based on publicly available information and user feedback as of July 2026.
Table of contents
- What we're building: before / after
- How it works: three roles
- Setup
- Demo 1: A thank-you and next-steps draft, minutes after the call
- Demo 2: Reply to a prospect's question, grounded in the transcript
- Demo 3: A Friday sweep for deals you never followed up on
- Tips and caveats
- Going further: the same pattern, other tools
- FAQ
What we're building: before / after
Before: After each call, you spend 30 minutes rereading notes and composing a recap email. In a busy week, the follow-up slips to the next day, and sometimes the prospect emails you first asking "any update on that?"
After: You ask Claude once ("draft a follow-up in Gmail from today's call notes") and minutes after the meeting ends, a draft with the decisions and next steps is sitting in your drafts folder. You review, adjust, send.
Two design choices make this feel safe. First, SuperIntern is a botless desktop meeting assistant: no bot joins your call, nothing asks your prospect for recording permission, and transcripts and AI summaries accumulate automatically. Second, the Gmail side of the integration stops at creating drafts. The AI cannot send email on your behalf; sending always happens by your hand. That two-layer setup is what lets you put AI into external communication, the one place where mistakes are expensive.
How it works: three roles
The integration is a combination of three players.
| Role | Player | What it does |
|---|---|---|
| Provide meeting data | SuperIntern MCP | Serves transcripts, AI summaries, and meeting notes, strictly read-only |
| Judge and write | Claude (the AI client) | Reads the notes and the email thread, composes the message for the purpose at hand |
| Take action | Gmail (connector) | Searches mail, reads threads, saves drafts |
MCP (Model Context Protocol) is an open standard for safely connecting AI assistants to external tools. SuperIntern's MCP exposes your meeting data to AI clients read-only, while Claude's official Gmail connector handles searching mail, reading threads, and saving drafts. In other words, it is Claude that writes into Gmail, not SuperIntern. Your SuperIntern data can never be modified by the AI, it can only see meetings you yourself can access, and because the Gmail connector has no send capability, the AI's work always stops at "a draft is waiting for you."
Setup
There are only two connections to make. Neither requires an API key, just a login screen.
1. Connect SuperIntern MCP to Claude
In Claude, open Settings → Connectors, choose "Add custom connector", and register the connection URL:
https://mcp.app.super-intern.com/mcp
A SuperIntern login screen opens; sign in and grant access. SuperIntern-side requirements (Plus plan or higher for personal workspaces, admin enablement on Enterprise) and setup steps for other clients like Claude Code and Cursor are covered in our MCP setup guide.
2. Connect Gmail to Claude
Add Gmail (part of the Google Workspace connectors) from Claude's connector list and sign in with your Google account. Plan availability on the Claude side varies, so check the official help article for current conditions.
To check both connections, try:
List my 3 most recent SuperIntern meetings and the subjects of my 3 latest unread emails
If both come back, you're ready.
Demo 1: A thank-you and next-steps draft, minutes after the call
The most frequent move is the one right after the call ends. Follow-up speed is the whole game, so as soon as SuperIntern generates the summary, you ask:
Get the AI summary of today's "Acme discovery call" and draft a follow-up
email in Gmail to Jordan at Acme.
Structure: thank you, then what we agreed today (3 bullets max), then
our homework with deadlines, then a proposal for the next meeting.
Keep the tone warm but professional, and match the style of emails
I usually send.
Claude extracts the decisions and open items from the summary, and a draft like this appears in your Gmail drafts folder:
Subject: Great talking today - recap and next steps
Hi Jordan,
Thanks for the time today. Here's a quick recap of where we landed:
- Security: SSO support is a hard requirement for rollout
- Trial scope: we'll start with 10 seats on your CS team for 2 weeks
- Pricing: formal quote to follow before the trial starts
On our side, we'll return the completed security questionnaire by Wednesday, Aug 5. Would you have 30 minutes late next week for a trial kickoff?
The draft exists while the call is still fresh in your head, so reviewing takes minutes. And because you said "match the style of emails I usually send," Claude can look at your sent mail and bend the phrasing toward how you actually write.
Demo 2: Reply to a prospect's question, grounded in the transcript
The hard part of follow-up isn't the first thank-you note; it's everything after. A few days post-call, the prospect writes: "Could you send more detail on the security setup you mentioned? I need it for an internal review."
A human now has to open the email thread and the meeting notes side by side and reconcile them from memory. Claude can read both at once.
Read the latest email from Jordan and draft a reply.
Before answering, check the transcript of the "Acme discovery call"
for what exactly we discussed about security, and make sure the reply
doesn't contradict anything I committed to in the meeting.
For anything we didn't cover in the call, say honestly that we'll
confirm and follow up.
The last sentence is the heart of this prompt. By explicitly forbidding promises that aren't in the record, you get a draft that separates "what we said in the meeting" from "what needs checking." The one failure mode sales teams fear most, an email answer that contradicts what was said on the call, gets prevented by the transcript acting as the source of truth.
Demo 3: A Friday sweep for deals you never followed up on
Beyond single calls, referencing multiple meetings at once is something only MCP makes easy. On Friday afternoon, run this:
List this week's meetings in the "Sales" project and identify the
external participants for each.
For each call, search my Gmail sent mail to check whether I sent a
follow-up after the meeting.
For the ones I haven't, draft a follow-up based on the meeting summary.
Finish with a table of sent vs. drafted.
Claude cross-references your meeting list with your sent mail, prepares drafts only where the follow-up is missing, and reports back:
Checked 5 sales calls this week.
- Acme (Mon): follow-up sent
- Brightline (Tue): follow-up sent
- Corely (Tue): not sent. Draft created
- Dover Labs (Wed): not sent. Draft created
- Everpeak (Fri): today's call, draft created
"I thought I sent that" stops being a thing, structurally. While you're at it, you can add "also summarize the key points from my previous meetings with next week's prospects" and turn the same Friday ritual into prep for the week ahead.
Tips and caveats
You always press send. By design, Claude can only go as far as a draft. Treat that as a safety feature, not a limitation: the tooling itself guarantees the rule that no external email leaves without human review.
Fix the structure in the prompt. Specifying the skeleton ("thank you, decisions, homework, next meeting ask") keeps output stable. A prompt that works is worth saving as a team snippet.
Forbid promises that aren't in the record. As in Demo 2, explicitly instruct that anything not discussed in the meeting should be marked as "to be confirmed." The transcript is your primary source; use it to keep AI drafts from embellishing.
Check recipients and names yourself, last. The body can be delegated; a wrong recipient or misspelled name costs trust. Keep your pre-send check exactly as it is.
Make the meeting data accurate at the source. The better company names, people, and product terms are transcribed, the better the drafts. Register frequent proper nouns in SuperIntern's custom dictionary.
Writes only happen in Gmail drafts. Your SuperIntern data is never modified through MCP. A draft you don't like gets discarded in Gmail, so the cost of a bad attempt stays near zero.
Going further: the same pattern, other tools
The pattern extends well beyond Gmail: SuperIntern MCP provides the data, Claude judges, and another tool receives the action.
- Slack: share call highlights into your sales channel. We covered the Slack side in detail in the first article in this series
- Task tracking: file the homework items from calls as Linear issues with owners, covered in the second article in this series
- CRM: extract the prospect's concerns and interests from the transcript and update your deal notes
We'll keep exploring these combinations in this series, one tool at a time, with real prompts.
FAQ
Q. Can I use SuperIntern MCP on the free plan?
A. No. Personal workspaces require the Plus plan or higher. Team plan workspaces can use it as is, and on Enterprise it works once an admin turns on "MCP access" in workspace settings.
Q. Can the AI send an email without me noticing?
A. No. Claude's Gmail connector can search mail, read threads, and create drafts, and that is all; it has no send capability. Sending always happens by you, in Gmail.
Q. Does SuperIntern write the drafts into Gmail?
A. No. Claude creates the drafts through the Gmail connector. SuperIntern MCP only provides meeting data read-only; SuperIntern itself never writes to external tools.
Q. Can the AI modify my meeting notes or transcripts?
A. No. Every SuperIntern MCP tool is read-only; no create, edit, or delete operations exist. The only writes happen in your Gmail drafts folder.
Q. Is it okay to let the AI read my email?
A. The Gmail connector only accesses the mailbox of the account you connect, and you can revoke access anytime from Google's security settings. For data handling details, see Anthropic's official help article.
Q. Does this work with AI clients other than Claude?
A. SuperIntern MCP supports MCP clients such as Claude Code, Codex, and Cursor. Gmail integration options differ by client, so check the connector or MCP support of the client you use.
SuperIntern already handles the "capture" half of your sales calls automatically. Now automate everything up to the moment before "send."