How to Use the Google Pub/Sub Subscription MCP in CrewAI

Let your CrewAI agent teams coordinate to pull, process, and acknowledge Google Pub/Sub messages autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Pub/Sub Subscription MCP to CrewAI

Create your Vinkius account to connect Google Pub/Sub Subscription 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 Google Pub/Sub Subscription with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent queue coordination

A researcher agent can run `pull_messages` to ingest raw data, while a specialized analyst agent processes the payload. This divides and conquers your queue workload automatically. After the team completes its task, a dedicated operator agent calls `acknowledge_messages` to clear the item. Clean handoffs across your entire crew prevent processing bottlenecks.

Autonomous MCP Server execution

Your crew uses the `pull_messages` tool to check for new tasks, routing the raw payloads to the appropriate agents. Running background operations without human intervention is the core of autonomous systems. Because the MCP Server is hosted in a secure environment, your autonomous crew can run continuously, pulling and committing messages as they arrive. This setup keeps your infrastructure load predictable and your queue processing fast.

Safe message lifecycle management

The `acknowledge_messages` tool ensures that once a crew member finishes processing, the message is permanently removed from Google Cloud. Preventing duplicate work across your agent team is critical for data integrity. This tight loop between pulling and acknowledging prevents other agents or external systems from grabbing the same workload. Your data pipeline remains consistent even under heavy message volume.

Setup guide

Set up Google Pub/Sub Subscription 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 Google Pub/Sub Subscription tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Google Pub/Sub Subscription 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 Google Pub/Sub Subscription. 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 Google Pub/Sub Subscription 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 Google Pub/Sub Subscription MCP in CrewAI

Pass the server URL to the specific agent's config. This limits the `pull_messages` and `acknowledge_messages` tools to the agent responsible for queue management.

The message will remain in the subscription queue. Once the visibility timeout expires, Google Cloud makes it available for another agent run to pull.

Yes. You can set up a sequential crew where the first agent calls `pull_messages` and the final agent in the pipeline calls `acknowledge_messages` after all work is done.

You connect using the MCPServerHTTP class or by passing the MCP endpoint URL directly into your crew's configuration, exposing the tools to your agents instantly.

Your subscription data and ack IDs are isolated in a secure, single-tenant runtime. No message content is ever cached or exposed to external networks.

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