Pipedrive MCP

Live

OAUTH 2.1

DEAL PIPELINE

CRM & Sales

Pipedrive MCP gives agents authenticated access to your deal pipeline: search contacts, create and update deals, log activities, and add notes.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Pipedrive MCP
agent · Acme Q3
Run
Move the Acme deal to Negotiation and log a follow-up call for Friday.
S
pipedrivemcp_updatedeal
97ms
Pipedrive agent
Deal 'Acme Corp - Renewal' moved to Negotiation. Follow-up call logged for Friday 2pm.
Sources: 1 deal, 1 activity
pipedrivemcp
1 deal
18:29
Message Claude...

Tools your sales agent reaches for on Pipedrive, scoped per user.

CALL ANY TOOL
Manage the deal pipeline end to end: search contacts, update deals, log activities, and add notes, scoped to each user's own Pipedrive access.
pipedrivemcp_addactivity
Addactivity
Creates a new activity (call, meeting, task, email, deadline, or lunch) and optionally links it to a deal, lead, person, or organization.
Parameters
Name
Type
Required
Description
attendees
array
Optional
List of calendar attendees for the activity.
busy
boolean
Optional
Whether the activity marks the user as busy in the calendar.
deal_id
number
Optional
The ID of the deal to link this activity to.
done
boolean
Optional
Whether the activity is marked as done.
due_date
string
Optional
The due date for the activity in YYYY-MM-DD format.
due_time
string
Optional
The due time for the activity in HH:MM format.
duration
string
Optional
The duration of the activity in HH:MM format.
lead_id
string
Optional
The UUID of the lead to link this activity to.
location
object
Optional
The location details for the activity.
note
string
Optional
A private note for the activity.
org_id
number
Optional
The ID of the organization to link this activity to.
owner_id
number
Optional
The ID of the user to assign this activity to.
participants
array
Optional
List of persons participating in the activity.
person_id
number
Optional
The ID of the person to link this activity to.
priority
number
Optional
The priority level of the activity.
project_id
number
Optional
The ID of the project to link this activity to.
public_description
string
Optional
A public note or description visible to all participants.
subject
string
Optional
The subject/title of the activity.
type
string
Optional
The type of activity (e.g., call, meeting, task, email, deadline, lunch).
pipedrivemcp_adddeal
Adddeal
pipedrivemcp_addnote
Addnote
pipedrivemcp_addorganization
Addorganization
pipedrivemcp_addperson
Addperson
pipedrivemcp_convertleadtodeal
Convertleadtodeal
pipedrivemcp_getactivities
Getactivities
pipedrivemcp_getactivity
Getactivity
pipedrivemcp_getdeal
Getdeal
pipedrivemcp_getdeals
Getdeals
pipedrivemcp_getleadconversionstatus
Getleadconversionstatus
pipedrivemcp_getnote
Getnote
pipedrivemcp_getnotes
Getnotes
pipedrivemcp_getorganization
Getorganization
pipedrivemcp_getorganizations
Getorganizations
pipedrivemcp_getperson
Getperson
pipedrivemcp_getpersons
Getpersons
pipedrivemcp_getstage
Getstage
pipedrivemcp_getstages
Getstages
pipedrivemcp_searchdeals
Searchdeals
pipedrivemcp_searchleads
Searchleads
pipedrivemcp_searchorganization
Searchorganization
pipedrivemcp_searchpersons
Searchpersons
pipedrivemcp_updateactivity
Updateactivity
pipedrivemcp_updatedeal
Updatedeal
pipedrivemcp_updatenote
Updatenote
pipedrivemcp_updateorganization
Updateorganization
pipedrivemcp_updateperson
Updateperson
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Pipedrive tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipedrivemcp"], toolNames: [
    "pipedrivemcp_searchpersons",
    "pipedrivemcp_getdeal",
    "pipedrivemcp_adddeal"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Move the Acme deal to Negotiation and log a follow-up call for Friday" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipedrivemcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Move the Acme deal to Negotiation and log a follow-up call for Friday" }],
  tools,
});

// Execute the tool call with the user's vaulted pipedrivemcp credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipedrivemcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Move the Acme deal to Negotiation and log a follow-up call for Friday" }],
  tools,
});

// Tool call runs with the user's vaulted pipedrivemcp credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipedrivemcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "pipedrivemcp_agent",
  model: "gemini-2.5-pro",
  instruction: "Pipedrive tools scoped to this user",
  tools,
});

await agent.run("Move the Acme deal to Negotiation and log a follow-up call for Friday");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Pipedrive MCP tool. Click to copy, paste into your agent, done.
Find contacts and deals
Copy the prompt
Copied
Search for a person named 'Sarah Kim'.
Copy the prompt
Copied
Get the full details of deal 4021.
Copy the prompt
Copied
Search persons at Acme Corp by email domain.
Move the pipeline
Copy the prompt
Copied
Move the Acme Corp deal to the Negotiation stage.
Copy the prompt
Copied
Create a deal for Globex worth $18,000 in the Proposal stage.
Copy the prompt
Copied
Mark deal 4021 as won.
Log activity
Copy the prompt
Copied
Log a follow-up call with Sarah Kim for Friday 2pm.
Copy the prompt
Copied
Add a note to deal 4021 about the pricing objection.
Copy the prompt
Copied
Create a task to send the contract by end of week.
SEE HOW AUTH WORKS
Your users connect once. Their Pipedrive MCP credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Pipedrive 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
2
Store
Their
Pipedrive 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
3
Resolve
When your agent calls a
Pipedrive 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
4
Audit
Every
Pipedrive 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 CRM and sales connectors.
GTM
Deal room sync agent
Pull opportunity context from Salesforce, capture decisions from Slack, and keep the Google Drive deal room doc current.
PEOPLE OPS
Performance review collector agent
Collect review feedback from Airtable and Google Forms per manager, summarise each report in Notion, and DM the digest in Slack.
PEOPLE OPS
Offer letter routing agent
Draft the offer in PandaDoc, gate it on hiring manager approval in Slack, then email the candidate their signature link.
SUPPORT
Support ticket automation (Google ADK)
Fetch, annotate, and archive Zendesk tickets with Notion context, digesting anything it cannot answer to Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Pipedrive MCP token looks fine in a demo. In production every deal update looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Pipedrive MCP today. Ten connectors 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 Pipedrive MCP as the user or through a shared key?
As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every Pipedrive MCP action in your audit trail is attributed to a real user, not a shared service account.
Where is the Pipedrive MCP token stored?
In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.
Can I limit what the agent does in Pipedrive MCP?
Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.
What happens when a user revokes access?
The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.
Can the agent close deals as won or lost without review?
Only if you scope updatedeal into the tool set you expose. Keep the agent to search and read tools for a read-only rollout, or require a human step before status changes to won or lost.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""pipedrivemcp"": {
""url"": ""https://mcp.scalekit.com/pipedrivemcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.pipedrivemcp]
url = ""https://mcp.scalekit.com/pipedrivemcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""pipedrivemcp"": {
""url"": ""https://mcp.scalekit.com/pipedrivemcp"",
""type"": ""http""
}
}
}