Lemlist MCP connector for AI agents

Tools your outbound sales agent reaches for on Lemlist MCP, scoped per user.

CALL ANY TOOL

Lemlist MCP exposes tools for managing campaigns, leads, sequences, and replies — giving agents control over the full multichannel outreach lifecycle.

lemlistmcp_add_contacts_to_list

List add contacts to

Add existing CRM contacts to a contact list by list ID.

Parameters

Name

Type

Required

Description

contactIds

array

Required

Contact IDs to add to the list (max 1,000)

listId

string

Required

Target contact list ID in clt_xxx format. Get valid IDs from get_contact_lists.

lemlistmcp_add_leads_to_campaign

Add Leads To Campaign

lemlistmcp_add_sequence_step

Add Sequence Step

Add a step to an existing campaign sequence. Use only for modifying already-created campaigns — not for initial campaign creation.

Parameters

Name

Type

Required

Description

campaignId

string

Required

Campaign ID (cam_xxx)

delay

number

Required

Days to wait after previous step. Must be 0 for "sendToAnotherCampaign" (the lemlist API does not accept a delay for this type, transfer is immediate).

sequenceId

string

Required

Sequence ID (seq_xxx)

userConfirmed

boolean

Required

Must be true after user confirms

altMessage

string

Optional

Alternative message variation for "linkedinSend" steps (used as second-attempt content when applicable).

conditionKey

string

Optional

Condition to check (REQUIRED when type is "conditional"). E.g. emailsOpened, linkedinInviteAccepted.

delayType

string

Optional

REQUIRED for all conditional steps. "within" = must happen within delay days, "waitUntil" = wait indefinitely. For field-check conditions (hasEmailAddress, hasLinkedinUrl, etc.), use "within" with delay 0.

emailStatusFilter

array

Optional

Only for hasEmailAddress condition. Filter by email verification status. E.g. ["deliverable"] to only match leads with deliverable email. Omit to check if any email exists.

index

number

Optional

Zero-based position where to insert the step (0 = first). Omit to append at the end. Use to insert warm-up steps before an existing step (e.g. Like + Comment before an Invite).

message

string

Optional

Message content (REQUIRED when type is "email", "linkedinSend", "whatsappMessage" or "sms"; OPTIONAL but recommended for "linkedinInvite"). For emails: the HTML body. For LinkedIn/WhatsApp/SMS/tasks: the message text.

method

string

Optional

REQUIRED when type="api". HTTP method (GET or POST) used by the webhook call. Limited to GET/POST to stay iso with the lemlist UI editor.

recordMode

string

Optional

linkedinVoiceNote only: "ai" generates audio from text via ElevenLabs (user adds the text after); "manual" (default) requires user-recorded audio after step creation.

scoreComparator

string

Optional

Only for hasScore condition. "$gte" = score is above or equal to threshold, "$lt" = score is below threshold. Defaults to "$gte".

scoreThreshold

number

Optional

Only for hasScore condition. Score threshold value (0-100). Defaults to 80.

subject

string

Optional

Email subject line. Required for the first email; omit for follow-ups to send as reply thread. Supports Liquid syntax: {{ firstName }}, {% if condition %}...{% endif %}

targetCampaignId

string

Optional

REQUIRED when type is "sendToAnotherCampaign". Target campaign ID (cam_xxx) the lead is moved to. Must belong to the same team as the parent campaign and not be archived. Avoid cycles (A -> B -> A).

title

string

Optional

Task title (for manual/phone steps). Short label displayed in the review UI.

type

string

Optional

Type of step. Use "conditional" for branching based on lead behavior, "sendToAnotherCampaign" to move a lead to another campaign, "api" to fire an outbound HTTP webhook (provide method and url).

url

string

Optional

REQUIRED when type="api". Webhook URL fired during sequence execution. Supports Liquid templating against lead variables (e.g. https://example.com/leads/{{ _id }}). For POST, the request body is automatically the lead data; custom bodies and custom headers are not supported.

lemlistmcp_add_unsubscribe

Add Unsubscribe

lemlistmcp_bulk_enrich_data

Bulk Enrich Data

lemlistmcp_bulk_get_enrichment_results

Bulk Get Enrichment Results

lemlistmcp_call_api

Call Api

lemlistmcp_check_domain_health

Check Domain Health

lemlistmcp_connect_email_account

Connect Email Account

lemlistmcp_create_campaign_from_proposal

Create Campaign From Proposal

lemlistmcp_create_campaign_with_sequence

Create Campaign With Sequence

lemlistmcp_create_contact_list

List create contact

lemlistmcp_create_or_update_company

Create Or Update Company

lemlistmcp_create_or_update_contact

Create Or Update Contact

lemlistmcp_create_webhook

Create Webhook

lemlistmcp_delete_company

Delete Company

lemlistmcp_delete_memory

Delete Memory

lemlistmcp_delete_sequence_step

Delete Sequence Step

lemlistmcp_delete_unsubscribe

Delete Unsubscribe

lemlistmcp_delete_watch_list

List delete watch

lemlistmcp_delete_webhook

Delete Webhook

lemlistmcp_disconnect_email_account

Disconnect Email Account

lemlistmcp_enrich_lead

Enrich Lead

lemlistmcp_get_campaign_details

Get Campaign Details

lemlistmcp_get_campaign_sequences

Get Campaign Sequences

lemlistmcp_get_campaigns

Get Campaigns

lemlistmcp_get_campaigns_reports

Get Campaigns Reports

lemlistmcp_get_campaigns_stats

Get Campaigns Stats

lemlistmcp_get_contact_lists

Get Contact Lists

lemlistmcp_get_inbox_conversation

Get Inbox Conversation

For more tools, view docs.

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="lemlistmcp")

mcp = MultiServerMCPClient({
    "lemlistmcp": {
        "url": "https://mcp.scalekit.com/lemlistmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "lemlistmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/lemlistmcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "lemlistmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/lemlistmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="lemlistmcp")
# Connect to MCP at https://mcp.scalekit.com/lemlistmcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Analyze & report

Copy the prompt

Copied

Which of my active campaigns has the highest reply rate this month and what's the subject line of its first email step?

Copy the prompt

Copied

Show me all leads who opened but never replied across my last 3 campaigns.

Copy the prompt

Copied

What is my current bounce rate and how does it compare to the previous 30-day period?

Copy the prompt

Copied

List every campaign launched in the last 90 days with their open, click, and reply rates side by side.

Manage leads

Copy the prompt

Copied

Add these 12 leads to my 'Q3 SaaS Outbound' campaign and skip any that are already enrolled.

Copy the prompt

Copied

Remove all leads marked 'notInterested' from my active campaigns and add them to the unsubscribe list.

Copy the prompt

Copied

List all leads in my 'Trial Expiry Follow-up' sequence who are still on step 1 after 5 days.

Deliverability & hygiene

Copy the prompt

Copied

Fetch sender stats for my primary email account for the last 30 days and flag if bounce rate exceeds 3%.

Copy the prompt

Copied

Unsubscribe anyone who replied with 'unsubscribe' or 'remove me' across all campaigns this week.

Copy the prompt

Copied

Pause any campaign where the bounce rate for the last 50 sends exceeds 5%.

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

Lemlist MCP

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

Store

Their

Lemlist MCP

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

Resolve

When your agent calls a

Lemlist MCP

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

Audit

Every

Lemlist MCP

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 connectors.

SALES

Outbound prospecting agent

Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.

Apollo

View agent

GTM

HubSpot to Slack updates agent

Watch HubSpot deal stage changes and post structured updates to the right Slack channel. Reps stop checking the CRM all day.

HubSpot

Slack

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

01.

Shared tokens break per-user analytics

A shared API key looks fine in a demo. In production every campaign action traces back to a service account, not the rep who owns the sequence. Scalekit resolves the real user credential so Lemlist audit logs stay meaningful.

// shared key
 audit → bot_service_account

// scalekit
 audit → rep_alice ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Lemlist MCP today. Others 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 Lemlist as the user or through a shared API key?

Scalekit resolves a per-user credential for each call. The Lemlist activity log shows the real account owner, not a shared service key, so campaign attribution and deliverability metrics stay accurate per sender.

Where is the Lemlist API key stored?

In Scalekit's AES-256 encrypted vault, isolated per tenant. Keys are resolved at request time and never passed through LLM context. Rotation or revocation takes effect immediately across all agents without code changes.

Can I limit what the agent is allowed to do in Lemlist?

Pass a toolNames filter to listScopedTools. Scalekit enforces the approved set before every API call — the agent cannot invoke tools outside that list, so you can restrict it to read-only reporting or block destructive operations like lead deletion.

What happens when a user revokes Lemlist access?

The credential is invalidated at the next tool call. The agent fails closed rather than falling back to a shared key. Other users' sessions are unaffected, and the revocation event is written to the audit log with a timestamp.

Can the agent accidentally add contacts to the wrong campaign or trigger unintended sends?

Scope your agent to a named toolNames list that excludes lemlist_leads_add and lemlist_campaigns_launch if you want read-only access. Scalekit enforces that list before every call, so write tools are unreachable unless you explicitly permit them. You can also restrict by campaign_id at the application layer before passing arguments to the tool.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit