How to Use the Front MCP in CrewAI

Q: How can I set up a CrewAI team to manage a Front inbox?

Assign an agent the listinboxthreads tool for monitoring. A second agent gets getconversationdetails for analysis, and a third gets sendinboxreply to act. You pass the MCP server URL to each agent in your crew setup.

Q: How does my crew know which inboxes are available to work with?

Have one of your agents call the listsharedinboxes tool at the start of its task. It can then share this list with the rest of the crew, so they all know the valid inboxes they can interact with.

Deploy autonomous agent crews to manage your Front inboxes. Let them monitor, triage, and reply to conversations 24/7.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Front MCP to CrewAI

Create your Vinkius account to connect Front 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 Front with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build an Autonomous Support Team

CrewAI lets you assign roles. Create a 'Triage Agent' that constantly runs `list_inbox_threads` on your main support inbox. When it finds a new conversation, it passes the ID to a 'Context Agent'. The 'Context Agent' then uses `get_conversation_details` and `list_conversation_messages` to understand the issue. Finally, it hands off to an 'Action Agent' that either drafts a response with `send_inbox_reply` or escalates by using `update_conversation_status` to assign it to a human.

Monitor and Respond with Specialized Agents

You can set up a 'Monitoring Agent' whose only job is to watch for negative sentiment. It can use `search_conversations` to find conversations with angry keywords. Once found, it triggers an alert for a human to review. This division of labor is what makes CrewAI different. Your agents collaborate. One agent can pull a list of teammates with `list_inbox_teammates`, while another uses that data to decide who gets the next high-priority ticket. This MCP server provides all the tools they need to work together on Front.

Automate Cross-Inbox Operations

Your agent crew isn't limited to a single inbox. A 'Router Agent' can use `list_shared_inboxes` to get a map of your whole Front setup. It can then move conversations from a general inbox to a specialized one, like 'Billing' or 'Sales'. This allows for complex, autonomous workflows. For example, if a message in the support inbox contains pricing questions, the crew can automatically move it to the sales inbox and assign it to a sales rep, all without any human touching it.

Setup guide

Set up Front 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 Front tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Front 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="Front Analyst",
        goal="Access and analyze Front data via MCP.",
        backstory="Expert analyst with direct Front access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Front 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 Front. 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 Front 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 Front MCP in CrewAI

Assign an agent the `list_inbox_threads` tool for monitoring. A second agent gets `get_conversation_details` for analysis, and a third gets `send_inbox_reply` to act. You pass the MCP server URL to each agent in your crew setup.

Absolutely. One agent can identify an issue needing escalation. It then passes the conversation ID to another agent in the crew, which uses `update_conversation_status` to re-assign the ticket to a senior support team's inbox.

Yes, this is a perfect task for a 'Research Agent'. Give it the `search_conversations` tool. It can execute a broad query, collect all the relevant conversation IDs, and then another agent can loop through them using `list_conversation_messages` to build a summary.

Have one of your agents call the `list_shared_inboxes` tool at the start of its task. It can then share this list with the rest of the crew, so they all know the valid inboxes they can interact with.

The crew only accesses the data its tools are designed for—specifically conversation contents, contact lists, and inbox metadata. Vinkius ensures the connection from the MCP server to Front is secure, and your agents authenticate using a single, revocable token, not your raw API key.

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