How to Connect Pipedrive to Claude: Official Connector vs Tugger
There are two ways to connect Pipedrive to Claude. Pipedrive has its own Claude connector, which you can add from Claude's connector directory and use to look up deals, contacts and activities in a chat. Tugger's Pipedrive connector takes a different route: it syncs your Pipedrive data on a schedule into a managed data warehouse and exposes that warehouse to Claude through a read-only MCP server. This guide covers both, explains what each is for, and walks through the Tugger setup step by step.
Option 1: Pipedrive's official Claude connector
If you want to ask Claude about what's in Pipedrive right now, the official connector is the place to start.
- In Claude, go to Settings, then Connectors.
- Find Pipedrive in the connector directory and choose Connect.
- Sign in to Pipedrive and approve the requested permissions.
- Start a new chat and switch the Pipedrive connector on.
Claude can then answer questions such as "which deals are in Proposal Sent" or "summarise the open opportunities for this account". Access follows the permissions of the Pipedrive user who connected it, and the connector can perform actions in Pipedrive as well as read from it, so it is worth checking what you have allowed before using it for anything beyond lookups.
Where the official connector stops
The official connector queries Pipedrive's API at the moment you ask. That suits interactive questions about the current state of the pipeline. It is less suited to reporting, for four reasons.
- History. Questions like "how has win rate by owner changed over the last six quarters" or "how long do deals sit in each stage" need every deal and every stage change over a long period. Pulling that through the API on each question is slow and often incomplete.
- Other systems. Pipeline value against invoiced revenue in Xero, or deals against billable hours in Harvest, means combining Pipedrive with data the Pipedrive connector cannot see.
- Consistency. Each answer is built from scratch, so two people asking the same question on the same day can get different numbers depending on how Claude filtered the data.
- Write access. A connector that can update deals is not one you want an analyst poking at with reporting questions.
For those cases you want Pipedrive in a warehouse, with Claude reading from the warehouse.
Option 2: connect Pipedrive to Claude through Tugger
Tugger syncs 49 tables from Pipedrive on a schedule: deals, leads, persons, organisations, activities, call logs, notes, products, pipelines and stages, plus the audit tables that record every field and stage change on a deal. Claude queries the warehouse through Tugger's MCP server, which is read-only, so nothing Claude does can change anything in Pipedrive.
Step 1: connect Pipedrive to Tugger
- Log in to Tugger, go to Connectors and choose Pipedrive.
- Sign in to Pipedrive when prompted and authorise Tugger to read your account.
- Choose a start date for the historical data you want to bring across and save.
Tugger runs a first sync and then refreshes on a schedule. You can see sync status and history in the Tugger dashboard.
Step 2: add Tugger's MCP server to Claude
- In Tugger, open AI Insights and copy your MCP server URL.
- In Claude, go to Settings, then Connectors.
- Choose Add custom connector.
- Name it "Tugger" and paste the MCP server URL.
- Click Add, then Connect, and sign in to Tugger when prompted.
In any new chat, open the connectors menu and switch Tugger on. Claude can now see the tables Tugger has synced from Pipedrive, and from any other system you have connected.
Step 3: ask your first question
"Show me open pipeline value by stage, and the average number of days deals have been in each stage."
Claude will identify the relevant tables, run the query and return the result. Because the stage-change history is in the warehouse, the second half of that question is answerable without any extra setup.
What you can ask
- What is our win rate by owner for each of the last six quarters?
- How long do deals spend in each stage before they are won or lost, and where do they stall?
- Which open deals over £10,000 have had no activity in the last 14 days?
- Which lead sources produce deals that actually close, and at what average value?
- For deals won this year, how does pipeline value compare with what we invoiced in Xero?
What syncs from Pipedrive
| Area | Tables |
|---|---|
| Sales | Deals, leads, pipelines, stages, deal products, discounts, installments, participants, goals |
| Deal history | Field and stage change log, participant change log, followers, files, emails |
| Contacts | Persons, organisations, organisation relationships, change logs, files, emails |
| Activities | Activities, call logs, notes, note comments |
| Products | Products and product fields |
| Projects | Projects, boards, phases, groups, plans, tasks |
| Users and configuration | Users, teams, custom field definitions, activity types, lead sources and labels, currencies |
Custom fields on deals, persons, organisations and activities come across with their definitions, so Claude knows what each one means.
Which should you use?
| Pipedrive's Claude connector | Tugger | |
|---|---|---|
| Best for | Looking things up and taking actions in a chat | Reporting and analysis |
| Data source | Pipedrive API at the time of asking | Managed warehouse, synced on a schedule |
| Historical and stage-change data | Limited | Full history from your chosen start date |
| Other systems in the same question | No | Yes, Xero, HubSpot, Harvest and 60+ others |
| Can change data in Pipedrive | Yes, within the user's permissions | No, read-only |
| Also feeds | Claude only | Claude, ChatGPT, Gemini, Power BI, Tableau |
Many teams end up using both: the official connector for day-to-day lookups, Tugger for the reporting layer. Tugger is UK-based and ISO 27001:2022 certified.
Related guides
- What is an MCP server?
- How to connect Xero to Claude
- How to connect Cin7 to Claude
- How to build a Claude dashboard
Get started
Connecting Pipedrive to Claude with Tugger takes no code and no faff. Try Tugger free for 10 days or book a demo and we'll walk through it with your own Pipedrive data.
