How to Use the Aidbase MCP in CrewAI

Q: Can I limit which Aidbase tools each agent in my CrewAI team can use?

Yes. When you configure the MCPServerHTTP connection in CrewAI, you can provide a toolfilter. This lets you assign specific Aidbase tools to specific agents, so your 'Responder' agent is the only one that can use sendaidbasereply.

Q: Can a CrewAI team manage multiple Aidbase chatbots at the same time?

Absolutely. A 'Manager' agent can call listaidbasechatbots to get a list of all active bots. It can then delegate the monitoring and management of each chatbot to a different sub-crew, allowing you to scale your autonomous operations.

Deploy autonomous Aidbase support teams with CrewAI. Assign roles for monitoring, analysis, and responding to customer issues.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aidbase MCP to CrewAI

Create your Vinkius account to connect Aidbase 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 Aidbase with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Knowledge Management Crew

This MCP Server allows you to build a team of agents to keep your knowledge base current. You can assign a 'Researcher' agent to find new information and a 'Writer' agent that uses `add_aidbase_faq_item` and `add_aidbase_website_knowledge` to add it to Aidbase. An 'Auditor' agent can periodically run `list_aidbase_knowledge` to get an inventory of all existing content and check for staleness. CrewAI manages the collaboration, creating a system that autonomously maintains your support documentation.

Run an Autonomous Support Desk

Deploy a full support team using CrewAI's multi-agent system. A 'Triage' agent can monitor for new messages using `list_aidbase_inboxes`. It then passes the ticket to an 'Analyst' agent, which uses `list_aidbase_chatbot_knowledge` to find answers. Finally, a 'Responder' agent takes the Analyst's findings and uses `send_aidbase_reply` to communicate with the customer. This creates a hands-off process for handling common support requests from start to finish.

Build a Proactive Monitoring Team

This MCP Server is not just for responding to customers; it's for monitoring the system itself. You can create a simple CrewAI team where one 'Operator' agent's only job is to call `check_aidbase_status` on a schedule. If the status is anything but operational, it triggers a 'Communicator' agent. That second agent can then take action, like using another tool to post a status update for your team. It's a simple way to build your own automated monitoring.

Setup guide

Set up Aidbase 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 Aidbase tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You create a crew of specialized agents. For example, one agent monitors Aidbase inboxes for new messages, a second agent finds answers in the knowledge base, and a third agent uses the `send_aidbase_reply` tool to answer the customer. CrewAI coordinates their work.

Yes. When you configure the `MCPServerHTTP` connection in CrewAI, you can provide a `tool_filter`. This lets you assign specific Aidbase tools to specific agents, so your 'Responder' agent is the only one that can use `send_aidbase_reply`.

The simplest method is to pass your Vinkius MCP Server URL directly into the `mcps` list when you define an agent. For example: `Agent(mcps=['https://...'])`. CrewAI handles the rest of the connection and tool discovery.

Absolutely. A 'Manager' agent can call `list_aidbase_chatbots` to get a list of all active bots. It can then delegate the monitoring and management of each chatbot to a different sub-crew, allowing you to scale your autonomous operations.

Yes. Your private knowledge base content is only ever accessed for the duration of a single tool execution. Each call runs inside a dedicated, single-use Vinkius sandbox, and all memory is erased the moment the task is complete.

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