What Pipedrive data can I access?

Deals, Persons, Organizations, Activities, Notes, and Pipelines. All data respects your Pipedrive permissions.

Can I create and update records?

Yes! Create and update deals, contacts, activities, and notes — all through natural conversation.

How does authentication work?

Uses your personal Pipedrive API token. Find it in Settings > Personal preferences > API. No OAuth flow needed.

Pipedrive Activities MCP Server for CrewAI 8 tools — connect in under 2 minutes

Name: Pipedrive Activities
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 8 Tools Framework

Connect your CrewAI agents to Pipedrive Activities through Vinkius, pass the Edge URL in the `mcps` parameter and every Pipedrive Activities tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Pipedrive Activities Specialist",
    goal="Help users interact with Pipedrive Activities effectively",
    backstory=(
        "You are an expert at leveraging Pipedrive Activities tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Pipedrive Activities "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 8 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Pipedrive Activities MCP Server

Connect Pipedrive CRM to any AI agent — manage your entire sales pipeline without switching tabs.

When paired with CrewAI, Pipedrive Activities becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Pipedrive Activities tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

Deals — Search, create, and update deals with pipeline tracking
Contacts — Find and create persons with email, phone, and organization
Organizations — Search companies linked to deals and contacts
Activities — Create calls, meetings, tasks, and emails
Notes — Attach notes to deals, persons, or organizations
Pipelines — View all pipeline stages and deal flow

The Pipedrive Activities MCP Server exposes 8 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Pipedrive Activities to CrewAI via MCP

Follow these steps to integrate the Pipedrive Activities MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 8 tools from Pipedrive Activities

Why Use CrewAI with the Pipedrive Activities MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Pipedrive Activities through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Pipedrive Activities + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Pipedrive Activities MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Pipedrive Activities for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Pipedrive Activities, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Pipedrive Activities tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Pipedrive Activities against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Pipedrive Activities MCP Tools for CrewAI (8)

These 8 tools become available when you connect Pipedrive Activities to CrewAI via MCP:

pd_activity_types

Default types: call, meeting, task, deadline, email, lunch. Teams can add custom types. Use to discover available activity types before creating activities, especially in accounts with custom configurations. List all activity types configured in Pipedrive — both default types (call, meeting) and custom types defined by the team

pd_create_activity

Subject and type are required. Type must be: call, meeting, email, task, lunch, or deadline (use pd_activity_types to see custom types). Set due_date (YYYY-MM-DD), due_time (HH:MM), and duration (HH:MM). Link to deals, persons, or orgs. Activities appear in the Pipedrive calendar and task queue for the assigned user. Schedule a sales activity in Pipedrive — a call, meeting, email follow-up, task, lunch, or deadline linked to deals or contacts

pd_deal_activities

Returns all scheduled, pending, and completed activities for that deal. Use when the user asks "what activities are on this deal?", "when is the next meeting for this deal?", or needs to review the engagement history of an opportunity. Get all activities (calls, meetings, tasks) linked to a specific deal for a complete activity history

pd_delete_activity

Consider marking as done (pd_mark_activity_done) instead to preserve history. Use only when the user explicitly wants to remove an activity from the record. Permanently delete a Pipedrive activity — this removes it from history and cannot be undone

pd_get_activity

Returns subject, type, dates/times, duration, notes, linked deal/person/org, and completion status. Use after listing activities to drill into a specific item. Get complete details of a specific Pipedrive activity by ID including notes, duration, and linked records

pd_list_activities

Returns subject, type (call/meeting/email/task/lunch/deadline), due date and time, whether it is done, and linked deal/person/org. Filter by done status: "true" for completed, "false" for pending/upcoming. Use when the user asks about tasks to do, scheduled meetings, overdue items, or recent sales activity. List Pipedrive activities (calls, meetings, tasks, emails) with due dates, types, and completion status

pd_mark_activity_done

The activity remains in history but is no longer in the pending/overdue queue. Use when the user says they completed a call, finished a meeting, or done with a task. Mark a Pipedrive activity as completed — removes it from the pending task queue and logs it as done

pd_update_activity

Only specified fields change. Use to reschedule (change due_date), rename (change subject), or reclassify (change type). Does not mark as done — use pd_mark_activity_done for that. Update an existing Pipedrive activity — reschedule, rename, or change type

Example Prompts for Pipedrive Activities in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Pipedrive Activities immediately.

"Search for deals with Acme Corp"

"Create a call activity for tomorrow at 2pm"

"Show me the pipeline stages"

Troubleshooting Pipedrive Activities MCP Server with CrewAI

Common issues when connecting Pipedrive Activities to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Pipedrive Activities + CrewAI FAQ

Common questions about integrating Pipedrive Activities MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.