Todoist integration with lemlist through MCP, with prompts to copy

A lead replies on LinkedIn. lemlist logs a manual task: send a follow-up message. You open Todoist to plan your afternoon and the task isn’t there, because nothing tells Todoist what just happened in lemlist. So you work from memory, or you miss the window entirely.

This happens dozens of times a week across a sales team. Tasks pile up in lemlist. Reps plan their day somewhere else. Nobody built the bridge, so people copy names and context by hand, or skip the step and let leads go cold.

A todoist lemlist integration through MCP closes that gap. Connect both MCP servers to the same AI client and an agent can pull your lemlist tasks into Todoist with full context, then report back when they’re done, so the two tools stay in sync without you touching a spreadsheet.

In this article, you’ll get the prompts to copy for both directions, what to check before you trust the output, and the guardrails to keep in place once an agent is writing in two tools at once.

Why connect lemlist and Todoist through MCP

lemlist generates manual tasks for every rep: calls to make, LinkedIn messages to send, emails that need a human touch. Many reps plan their day in Todoist, which means the two task lists drift apart the moment a new step fires. When both MCP servers are connected in the same AI client, an agent keeps them in sync without exports or copy-paste.

An MCP server is a lightweight interface that lets an AI agent read and write data inside a specific tool. Each server exposes a set of actions the agent can call during a conversation. You can learn more about how this works for sales teams in the guide on MCP for sales.

With the lemlist MCP and the Todoist MCP running side by side, the agent can pull today’s manual outreach tasks from lemlist, push them into Todoist with full lead context, and later mark them complete in both places. No Zapier step, no CSV, no tab switching.

What you need before you start

Three things should be in place before you paste your first prompt:

• •

  The lemlist MCP connected in Claude, ChatGPT or Cursor. Follow the walkthrough on how to set up the lemlist MCP if you haven’t done this yet.

• •

  The Todoist MCP connected in the same AI client so the agent can reach both tools in one conversation.

• •

  Permissions scoped to what the use cases below actually need. Give the agent read access to both tools first, then expand to write access once you trust the output.

Start with read-only prompts. Let the agent show you what it would do before you let it change anything in either tool.

1. Daily task list with context

Every morning, reps open lemlist to see which leads need a call or a LinkedIn message, then open Todoist to plan their day. The context lives in one tool and the to-do list lives in another, so reps spend the first chunk of their morning copying names and notes between tabs.

Paste this prompt into your AI client:

The agent reads your pending manual tasks from lemlist, grabs each lead’s name, company, and the step they are on, then creates a Todoist task for each one with that context in the description. Your daily list now has everything you need to pick up the phone or write a message without switching back to lemlist.

Before you run this on a full campaign, test it on a single sequence with a small group of leads. Confirm the Todoist tasks land in the right project and that the descriptions contain accurate lead data. Knowing the right call dispositions to log will also help you close the loop faster once you start dialing.

2. Close the loop when tasks are done

Finishing a task in Todoist does not update lemlist. If a rep forgets to go back and mark the step complete, the sequence stalls and the lead sits in limbo until someone notices.

Paste this prompt into your AI client:

The agent scans your completed Todoist tasks, matches each one back to the original lemlist task using the lead and step details stored in the description, and marks the corresponding lemlist task as done. The sequence advances and the next step fires on schedule.

Before running this across every completed task, verify on a small batch that the agent matches the right leads. A mismatch could mark the wrong step complete and skip a touchpoint.

Guardrails when an agent works in lemlist and Todoist

Letting an agent write in two tools at once is powerful, but it needs boundaries. Keep these in place:

• •

  Review every campaign before launch. The agent can build sequences, but a human should approve messaging, timing, and audience before anything sends.

• •

  Test on ten leads first. Run each new prompt on a small batch, check the results, then scale.

• •

  Keep unsubscribes and exclusion lists active. These protect your domain reputation and keep you compliant regardless of what the agent creates.

• •

  Decide who on the team can connect the MCPs. Limit access to people who understand the outreach workflow and can spot errors.

• •

  Log what the agent changed. After each session, ask the agent to list every task it created or updated. Save that log so you can audit later.

These guardrails matter more as you add prompts. The goal is to track the SDR metrics that tell you whether the agent is helping or creating noise.

Run it in lemlist

The lemlist MCP server works in Claude, ChatGPT and Cursor. Once connected, the agent can do far more than sync tasks with Todoist.

It can search the People database with 650M+ contacts and 65M+ companies to find leads that match your ICP. It can enrich those leads with waterfall enrichment across 14+ providers to get verified emails and phone numbers. It can create campaigns and sequences across email, LinkedIn, calls and WhatsApp, then read the unified inbox and campaign stats to tell you what is working. And it can act on intent signals to trigger outreach when a lead is most likely to engage.

Every one of these actions is available as a prompt in a single conversation. You can explore the full list of lemlist MCP use cases to see what else the agent can handle beyond task management.

Final takeaway

Todoist and lemlist serve different jobs, but the data between them should flow without manual work. MCP makes that possible by letting an agent read and write in both tools from one conversation. The two prompts in this article give you a starting point you can test today.

Build your first signal-based sequence in lemlist.