How to Use the Sobot MCP in CrewAI

Q: What type of data does Sobot touch regarding privacy?

The MCP Server touches customer identity (listusers) and communication records via listchathistory. Any agent handling this must respect the data's sensitive nature.

Q: Can I use the Sobot MCP Server in crewai?

Yes. You pass the necessary tools—like createticket or listagents—directly to your agents when setting up the process. The framework handles calling these tools across multiple, specialized roles.

Q: How does crewai manage tool calls from Sobot?

It maps the available tools (like getticketdetails) into callable functions for each agent's role. This means Agent A knows it can call that specific function, and Agent B can use its output.

Q: Is the Sobot MCP Server suitable for complex workflows with crewai?

Absolutely. Because the tools are highly structured (e.g., listagents returns a list of objects), they fit perfectly into crewai's role-based, sequential execution model.

Run Autonomous Teams with crewai: Deploy multi-agent operations across the Sobot support ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sobot MCP to CrewAI

Create your Vinkius account to connect Sobot to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sobot with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Triage and Escalation Pipelines

Assign a 'Triage Agent' to use `list_tickets` to pull all recent customer requests. Then, assign an 'Expert Agent' to run `get_ticket_details` on the most complex ones. The agents collaborate by passing findings to each other in shared memory. This isn't one agent doing everything; it’s a structured handoff process where roles are specialized and output is combined for a final, actionable recommendation.

Knowledge Synthesis Agent

Build an 'Research Agent' that uses `list_knowledge` to gather multiple potential articles. A second 'Synthesis Agent' then cross-references those results with current user details pulled via `list_users`. This creates a comprehensive answer set. The shared memory ensures the Synthesis Agent knows exactly which users and which knowledge gaps were identified during the research phase.

User Profile Management

Create a 'Profile Agent' that uses `list_users` to pull customer data. If needed, it can then call `get_org_summary` to check if recent organizational activity suggests a specific service issue, allowing the team to tailor the response. The agents work sequentially: first gathering identity, then checking context, and finally drafting the action plan.

Setup guide

Set up Sobot 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 Sobot tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

CrewAI is built for this. You define specialized agents—one to list tickets, one to read history, and a third to summarize findings. The collaboration happens through shared memory, making the entire process autonomous.

The MCP Server touches customer identity (`list_users`) and communication records via `list_chat_history`. Any agent handling this must respect the data's sensitive nature.

Yes. You pass the necessary tools—like `create_ticket` or `list_agents`—directly to your agents when setting up the process. The framework handles calling these tools across multiple, specialized roles.

It maps the available tools (like `get_ticket_details`) into callable functions for each agent's role. This means Agent A knows it can call that specific function, and Agent B can use its output.

Absolutely. Because the tools are highly structured (e.g., `list_agents` returns a list of objects), they fit perfectly into `crewai`'s role-based, sequential execution model.

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