How to Use the ThinkStack MCP in CrewAI

Q: How do I check ThinkStack status with CrewAI?

You run checkthinkstackstatus directly. This verifies the connectivity of your entire MCP Server setup before you kick off a multi-agent workflow.

Q: Where does ThinkStack and CrewAI list all available bots?

It's simple: use listbots. This tool gives you an inventory of every specialized agent running in your crew. You can then inspect any one bot using getbot.

Q: How do I view all possible steps or functions for my agents using ThinkStack and CrewAI?

You call listactions. This gives you a complete list of the actions that can be executed across your entire multi-agent system. It's crucial for debugging workflows.

Build complex, multi-agent operations using ThinkStack and CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ThinkStack MCP to CrewAI

Create your Vinkius account to connect ThinkStack 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 ThinkStack with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Define Agent Roles and Tools

You start by listing the agents with `list_bots` to see what specialized bots you have. Then, use `get_bot` if you need specific details on a single bot's profile. If an agent needs new capabilities, define them using `add_source`, giving it access to external knowledge or tools.

Orchestrate Bot Actions

The core of the workflow is defining what actions are possible. Call `list_actions` to see the full set of available functions for your crew. You'll then use these definitions when building complex, multi-step processes. Need to change a tool? The server lets you manage this via its API endpoints.

Track Shared Memory and Process State

For autonomous operations, remembering the context is everything. Use `list_conversations` to see every session that has run through your crew. You can then grab details on a specific thread using `get_conversation`. This shared memory allows one agent's output to become another agent's input without needing manual handoffs.

Setup guide

Set up ThinkStack 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 ThinkStack tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You run `check_thinkstack_status` directly. This verifies the connectivity of your entire MCP Server setup before you kick off a multi-agent workflow.

It's simple: use `list_bots`. This tool gives you an inventory of every specialized agent running in your crew. You can then inspect any one bot using `get_bot`.

It manages the definition and state of bot actions, which is a structural tool definition data type. The server tracks what tools are available to your autonomous crew members.

You call `list_actions`. This gives you a complete list of the actions that can be executed across your entire multi-agent system. It's crucial for debugging workflows.

Yes. The server handles knowledge source data. When you add or delete sources, the content remains managed by ThinkStack, maintaining system integrity for your crew.

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