How to Use the Intercom MCP in CrewAI

Q: How do I give multiple CrewAI agents access to Intercom tools?

You define the Vinkius URL in the mcps array when initializing your crew. This shares the entire MCP toolset, allowing your triage agent to use listconversations while your responder agent uses replytoconversation.

Q: Can CrewAI agents search Intercom contacts autonomously?

Yes, your research agent can invoke searchcontacts to find customer profiles based on custom attributes. The agent then shares these details with the rest of the crew via their collective memory.

Q: How do I limit which Intercom tools a CrewAI agent can use over MCP?

Use MCPServerHTTP from the crewai.mcp library to set up a toolfilter. This lets you restrict your research agent to listarticles while reserving replytoconversation for the writing agent.

Run autonomous support teams in CrewAI that research, tag, and resolve conversations via our Intercom MCP Server.

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

Multi-agent inbox triage in CrewAI

The `list_conversations` tool allows your triage agent to scan the entire support inbox for unresolved tickets. This agent analyzes the initial customer query, determines the technical difficulty, and hands it off to a specialized support agent. Because CrewAI supports shared memory, the downstream agent receives the full context without re-querying the API. This multi-agent coordination ensures that complex technical issues are identified and routed immediately.

Autonomous help center research

The `list_articles` tool gives your research agent access to your entire public knowledge base. When a customer asks a technical question, the researcher finds the matching article and extracts the solution steps. This MCP Server integration allows your autonomous crew to resolve common queries without human intervention. A separate writing agent then takes those steps and uses `reply_to_conversation` to draft a clear, friendly response.

Company profile enrichment

The `list_companies` tool lets your account management agent look up organizational details for incoming leads. The agent cross-references this with `get_contact` to build a complete profile of the customer's team size and spend. The crew uses this data to prioritize high-value tickets. If a contact belongs to an enterprise company, the moderator agent escalates the conversation, while applying tags using `list_tags` to keep the dashboard organized.

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

You define the Vinkius URL in the `mcps` array when initializing your crew. This shares the entire MCP toolset, allowing your triage agent to use `list_conversations` while your responder agent uses `reply_to_conversation`.

Yes, your research agent can invoke `search_contacts` to find customer profiles based on custom attributes. The agent then shares these details with the rest of the crew via their collective memory.

Use `MCPServerHTTP` from the `crewai.mcp` library to set up a `tool_filter`. This lets you restrict your research agent to `list_articles` while reserving `reply_to_conversation` for the writing agent.

Yes, you can run a sequential crew where one agent gathers data using `get_conversation` and the next drafts the reply, or a hierarchical crew where a manager agent assigns these tasks dynamically.

All API requests are routed through a single-use, sandboxed V8 execution thread that does not persist data. Your admin list and help articles are processed in-memory and immediately destroyed once the crew completes its task run.

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