How to Use the CrewAI Platform MCP in Google ADK

Q: Can my Google ADK agent write CrewAI Platform run logs to BigQuery?

Yes. Your agent can call getrunstatus to pull vault limits and execution logs, then format that data to write directly into your BigQuery tables.

Run complex CrewAI Platform tasks using Google ADK and feed long-context Gemini models with this 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 CrewAI Platform MCP to Google ADK

Create your Vinkius account to connect CrewAI Platform to Google ADK 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 CrewAI Platform with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Gemini long-context runs with CrewAI Platform data

The `list_crews` tool extracts CRM records directly from your headless CrewAI Platform setup. This lets your Google ADK agent pull entire account histories and feed them into Gemini's million-token context window. Your agent can also run `get_crew` to parse structural properties. Combining this with BigQuery data gives your Google Cloud agents a complete picture of your operations.

Start and cancel jobs via this MCP Server

The `kickoff_crew` tool initiates new runs with custom JSON payloads, setting up hard customer bindings on the fly. Your Google ADK agent handles the execution pipeline without leaving the Vertex AI environment. If a run encounters plan math errors or exceeds budget limits, your agent can call `cancel_run` to stop it. This keeps your Google Cloud infrastructure costs under tight control.

Track tasks and webhooks inside Google ADK

The `list_tasks` tool sends validation checks to route explicit gateway history right into your agent. It helps your Google ADK system verify task status before moving to the next step of a pipeline. Use `list_webhooks` to identify active arrays and hold states. Your Gemini-powered agent reads these webhooks to trigger external Vertex AI pipelines or update BigQuery tables.

Setup guide

Set up CrewAI Platform MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with CrewAI Platform tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="CrewAI Platform_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CrewAI Platform tools via MCP.",
    tools=mcp_tools,
)

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 CrewAI. 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 CrewAI Platform 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 CrewAI Platform MCP in Google ADK

Install the google-adk package and create an McpToolset pointing to your Vinkius HTTP endpoint. Pass this toolset into your LlmAgent constructor to instantly expose all CrewAI capabilities to Gemini.

Yes. Your agent can call `get_run_status` to pull vault limits and execution logs, then format that data to write directly into your BigQuery tables.

Gemini's massive context window easily processes all ten tools. You can use the optional tool_names filter in your Google ADK setup if you want to limit access to sensitive tools like `cancel_run`.

You can run your Google ADK script anywhere, including your local machine. It connects to the hosted MCP Server over a secure, authenticated HTTP connection managed by Vinkius.

Your gateway auth tokens and vault limits are processed inside an isolated, zero-trust V8 sandbox. Vinkius handles the authentication headers so your Gemini agent never exposes raw credentials to external logs.

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