How to Use the Intercom MCP in CrewAI

Q: How do I assign Intercom MCP Server tools to a specific CrewAI agent?

Pass the server URL directly in your agent's mcps list. You can limit tools so your researcher only gets listhelparticles while your support agent gets replytoconversation.

Q: Can a CrewAI team search Intercom contacts across different agents?

Yes. CrewAI agents share memory, meaning the agent running searchcontacts can pass the customer's ID directly to another agent responsible for updating their profile.

Q: Can I restrict agents from replying to customers directly?

Yes. You can exclude replytoconversation from the tools passed to your crew. This lets the agents analyze conversations and suggest drafts without ever sending messages.

Deploy teams of specialized agents to monitor Intercom conversations and update contacts autonomously using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Intercom MCP to CrewAI

Create your Vinkius account to connect Intercom to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Intercom with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CrewAI MCP Server workflows

Single agents get overwhelmed by complex tickets, but your crew can analyze history with `get_conversation_details` to coordinate responses. This MCP Server lets you build a crew where one agent analyzes history and another drafts the solution. The agents pass data back and forth using shared memory. While your research agent finds the right help center links, your writer agent packages them into a clean response.

Autonomous contact enrichment

Keep your customer records clean without manual data entry by running `list_contacts` to find incomplete profiles. Your crew collaborates to search external sources, verify the data, and update the profile using `create_contact` through this MCP integration. It turns your support history into clean, actionable sales leads.

Proactive conversation monitoring

Build a background crew that lists active threads via `list_conversations` to watch your inbox. When a critical issue pops up, the crew assigns it to the right person. It can draft an immediate response with `reply_to_conversation` or assign the ticket directly by looking up team members with `list_admins`.

Setup guide

Set up Intercom MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Intercom tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Intercom Analyst",
    goal="Access and analyze Intercom data via MCP.",
    backstory="Expert analyst with direct Intercom access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Intercom transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

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

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Intercom Analyst",
        goal="Access and analyze Intercom data via MCP.",
        backstory="Expert analyst with direct Intercom access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Intercom transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

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

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Intercom. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Intercom now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Intercom MCP in CrewAI

Pass the server URL directly in your agent's `mcps` list. You can limit tools so your researcher only gets `list_help_articles` while your support agent gets `reply_to_conversation`.

Yes. CrewAI agents share memory, meaning the agent running `search_contacts` can pass the customer's ID directly to another agent responsible for updating their profile.

The framework manages tool execution sequentially or hierarchically. This structure prevents your agents from spamming tools like `list_conversations` and hitting API rate limits.

Yes. You can exclude `reply_to_conversation` from the tools passed to your crew. This lets the agents analyze conversations and suggest drafts without ever sending messages.

Your customer profiles and support transcripts are processed inside ephemeral containers. The MCP server runs with zero-trust network policies to ensure your support data is never cached or leaked.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript