Rémi KokabiNovember 4, 20266 min read
Slack and lemlist integration, native sync and MCP workflows
Someone drops a target account in #target-accounts. Someone else posts a deliverability warning in #deliverability. A rep gets a reply in lemlist and mentions it in #sales. Three signals, three channels, zero action, because nobody is sitting there turning Slack messages into lemlist campaigns.
That gap is what a proper slack lemlist integration through MCP is built to close. Instead of a notification you glance at and forget, an agent reads what your team posts and acts on it inside lemlist: finding leads, launching sequences, running audits.
In this article, I’ll show you exactly how to set this up and give you the prompts to copy right now. You’ll see what to connect, what to check before letting an agent write in either tool, and three workflows you can run this week without touching a line of code.
Your team already talks about leads, accounts, and alerts in Slack all day. The only thing missing is a way to make that talk turn into outreach.
Why connect lemlist and Slack through MCP
lemlist already has a native Slack integration that pushes notifications when a lead replies, clicks, or unsubscribes. That covers live alerts. MCP goes further: an agent can read what your team posts in Slack and act on it inside lemlist, or pull lemlist campaign data and summarize it in the format each channel needs.
An MCP server is a lightweight layer that exposes a tool’s actions to an AI client over a standard protocol. The AI client connects to the server, discovers the available actions, and calls them during a conversation. You can read more about how this applies to outbound in the MCP for sales guide.
When both the lemlist MCP server and a Slack MCP server are connected in the same client, the agent can chain actions across the two tools in a single prompt. Read a channel, find leads, add them to a campaign. Pull campaign stats, format a digest, post it. The connection turns Slack from a notification endpoint into a trigger for real outbound work.
What you need before you start
The lemlist MCP server connected in Claude, ChatGPT, or Cursor. Follow the steps in how to set up the lemlist MCP to generate your API key and add the server URL to your client.
A Slack MCP server connected in the same client, so the agent can read channels and post messages in your workspace.
Permissions scoped to what the use cases below actually need. Give the Slack server read access to the channels you reference and write access only to the channels where the agent should post.
Start with read-only prompts. Let the agent pull data and show you the output before you allow it to write in either tool.
1. Morning digest of replies and signals
Reps open their day across five tabs: the lemlist inbox, CRM, Slack, email, and a spreadsheet someone forgot to update. By the time they know who replied overnight, the window to follow up has already shrunk.
Every morning, post in #sales the interested replies and new signals from lemlist, grouped by owner.
The agent reads the lemlist unified inbox for replies marked as interested, pulls recent buying signals, and groups everything by campaign owner. It then writes one Slack message per owner in #sales, so each rep sees only their accounts.
Before running this on your full list, confirm the agent is reading the correct campaign set and that the #sales channel is limited to the team that should see reply data.
2. Prospect accounts the team drops in a channel
AEs spot target accounts during calls, in news, or on LinkedIn and drop the company name in a Slack channel. That is where the intent dies. Nobody exports the list, nobody searches for contacts, and nobody adds them to a campaign.
Read the accounts posted in #target-accounts this week, find three decision makers at each, and add them to campaign X.
The agent reads #target-accounts, extracts company names from the messages, searches the lemlist lead database for decision makers at each company, and adds the matching leads to the campaign you specify. The lead database covers 650M+ contacts across 65M+ companies (lemlist internal data), so the agent can usually find verified contacts without leaving the conversation.
Before running this on a full list, check that the campaign exists, that the sequence is reviewed, and that the leads the agent found match your ICP filters.
3. Deliverability alerts with the fix
A misconfigured SPF record or a warming domain that fell behind can tank inbox placement for days. Most teams discover the problem only after reply rates drop, because nobody runs the audit on a schedule.
Run a deliverability audit on my domains and post the issues ranked by impact, with the fix for each, in #deliverability.
The agent runs the lemlist deliverability audit and DNS checks on your sending domains, ranks the issues by severity, and posts a summary in #deliverability with a one-line fix for each. If you want to go deeper on the fixes, the email deliverability guide covers the full checklist.
Before running this across all domains, verify the agent has access to every sending domain in your workspace and that the #deliverability channel is visible only to the people who manage infrastructure.
Guardrails when an agent works in lemlist and Slack
Letting an agent write in two tools at once is powerful and risky in equal measure. Keep these in place:
Review every campaign the agent creates before you launch it. The agent can build the sequence, but a human should approve the copy, the audience, and the send schedule.
Test on 10 leads first. Run the prompt on a small batch, check the output in both Slack and lemlist, then scale.
Keep unsubscribes and exclusion lists active. The agent respects the rules you set in lemlist, but only if those rules exist.
Limit who on the team can connect the MCP servers. One misconfigured permission can give the agent access to channels or campaigns it should not touch.
Log what the agent changed. After each run, ask the agent to list the leads it added, the messages it posted, and the campaigns it modified. Save that log.
Run it in lemlist
The lemlist MCP server works in Claude, ChatGPT, and Cursor. Once connected, the agent can do the following from a single conversation:
Search the lead database (650M+ contacts, 65M+ companies) by role, industry, company size, tech stack, and more.
Enrich leads with waterfall enrichment across 14+ providers to get verified emails and phone numbers.
Create campaigns and sequences across email, LinkedIn, calls, and WhatsApp.
Read the unified inbox and campaign stats to spot what is working and what needs a rewrite.
Act on intent signals so outreach lands when accounts are actively in market.
Every prompt in this article chains the Slack MCP with one or more of those capabilities. You can find more workflows in the full list of lemlist MCP use cases.
Final takeaway
The native Slack integration handles live notifications. MCP handles the work that should happen after those notifications, or before them. Connect both servers in the same AI client and you turn Slack channels into triggers for prospecting, deliverability fixes, and daily digests that write themselves.
Launch AI outbound campaigns
Automate prospecting and personalize AI-powered sequences to book more meetings.