CRMConnector
Pipedrive
Read and write Pipedrive deals, people, organisations, activities, leads and notes from Claude or ChatGPT through Tulina's MCP server, on your own API token.
Official site: app.pipedrive.com
What it can do
2 write
- 01Write
Read and write deals, people, organisations and activities
- 02Write
Create and update leads and the notes attached to a record
The connector works with your own Pipedrive account and one personal API token. It reads and writes deals, people, organisations, activities and products, searches across them, and handles leads and notes. A workflow that moves a deal to a new stage can log why it moved in the same run.
Does Pipedrive have an MCP server?
Yes. Pipedrive launched its own in June 2026 and hosts it at https://mcp.pipedrive.ai/mcp. You add it to Claude as a custom connector and sign in to Pipedrive in the browser. The assistant then acts with your Pipedrive role and visibility settings. Pipedrive's tool list covers reads, searches and writes on activities, deals, people, organisations, leads, products and notes, and it lists no delete tool. Tulina's connector is the other route, held in the same MCP link as the rest of your tools.
How do you connect Pipedrive to Claude and ChatGPT?
Through Tulina's MCP server, in three steps:
- In Pipedrive, open Personal preferences, then API, and copy your personal API token.
- Paste the token into Tulina's Pipedrive connector. The account subdomain is optional:
acmeforacme.pipedrive.comroutes requests to the right data center. The token is stored in the vault and never shown to the model. Several Pipedrive accounts can be connected, each under its own name. - Add
https://mcp.tulina.ai/mcpto Claude or ChatGPT and sign in with your Tulina account. The MCP page has the same link.
Tulina vs Pipedrive's official MCP server
Pipedrive's server is the first-party route and signs in as you through OAuth. Tulina's takes an API token and reaches Pipedrive beside your other tools.
| Pipedrive's MCP server | Tulina | |
|---|---|---|
| Endpoint | mcp.pipedrive.ai/mcp, hosted by Pipedrive | mcp.tulina.ai/mcp, one link for every connected tool |
| Sign-in | Pipedrive account, authorized in the browser | A personal API token in Tulina's vault |
| Deals, people, organisations, activities, products | Read, search, add and update | List, get, create, update and delete, plus a fields listing for custom field keys |
| Pipelines and stages | Read stages | List and get pipelines and stages |
| Leads | Read, search, add, update, convert to a deal | List and create |
| Notes | Read, add and update | List and create |
| Delete | No tool listed | Delete a record |
If the model should update a lead, edit a note or convert a lead to a deal, Pipedrive's own server is the better choice. Tulina fits when the Pipedrive step belongs to a longer piece of work that also touches your inbox, your calls or your messaging.
How does Tulina read a large Pipedrive account?
Lists come back one page at a time with a cursor, up to 500 records a page. The agent can narrow a list by owner, pipeline, stage or deal status, by a saved Pipedrive filter, or by an updated_since timestamp, so a daily check reads only what changed. Searching runs across deals, people, organisations, products and leads, either one entity at a time or across several object types at once. If you connect more than one Pipedrive account, each carries its own name and the agent picks one per call, or asks which when no default is set.
What you can ask it
"Which open deals in the Proposal stage haven't changed in two weeks?" The agent reads the pipelines and stages, lists open deals with updated_since, and returns the stale ones with their owners.
"Find everyone at Acme and log that we spoke today." The agent searches persons and organisations for Acme, then attaches a note to the right deal or person. A note takes exactly one target.
"Create a lead for Marie at Northwind from this email." The agent creates a lead that points at her person or organisation, with an amount and an expected close date if you give them. It looks up the custom field keys first when your account has client-specific fields.
Pipedrive pairs with HubSpot when a team runs two CRMs during a migration, and with Salesforce for the same questions on a different pipeline.
What the Pipedrive connector can't do
- It does not update a lead, convert a lead to a deal or edit a note. Those are create and list only.
- Custom fields are keyed by a 40-character hash, so the agent reads the fields listing before it writes client-specific data.
- Delete removes the record. Ask the agent to name the record and confirm before it deletes.
- No tool walks through several Pipedrive accounts at once. A total across accounts is one call per account.
Why through Tulina
The connection was never the hard part.
Most systems now publish their own way for a model to reach them, and that is good: it is what Tulina connects to. The hard part is deciding who may use it, what it is allowed to return, and what the model knows before it asks.
The keys stay in one place
YouTeamOrganisation
Connect Pipedrive once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that, so nobody is blocked and nobody holds more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
fields droppedmasked or hashedpseudonymised
Roles decide who can reach Pipedrive at all. Beyond that, a policy on the connector itself decides what comes back. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
whatwhowhen
Runs are logged for the organisation. That is what makes an automated action reviewable after the fact, and it is what a security review asks for first.
The run starts knowing your company
namingkey accountsdecisions
A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against Pipedrive returns something usable instead of something generic.
Processes that run on Pipedrive
None published yet.