How to Use the Sirv MCP in CrewAI

Q: How does crewai manage multiple Sirv tools?

You expose tools selectively using toolfilter when setting up the MCP Server connection. This ensures that only relevant functions, like searchfiles, are available to specific agents.

Q: Does the MCP Server support advanced tool exposure in crewai?

It does. You can use MCPServerHTTP from crewai.mcp along with a specific toolfilter to control exactly which functions your agents see.

Run autonomous operations against Sirv using the crewai framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sirv MCP to CrewAI

Create your Vinkius account to connect Sirv 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 Sirv with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Full Account Discovery

You can assign an 'Auditor' agent to run `list_account_users` and another 'Resource Manager' agent to use `list_custom_domains`. The team collaborates by passing the full list of domains, allowing a third 'Validator' agent to then call `get_file_details` for key assets. This role-based specialization lets you map out complex dependencies across your Sirv account structure.

Billing and Usage Analysis

Assign one agent to handle finance. This agent runs `get_billing_info` to get the costs, while a second 'Analyst' agent uses `get_detailed_usage` to compare those metrics against actual consumption data. The team generates a comprehensive usage report. This collaboration pattern is perfect for autonomous monthly financial reconciliation tasks.

Content Management Teams

Need to manage content? One agent can run `search_files` to find all relevant assets. A second 'Cleanup' agent then uses `delete_file` on the identified items, and a final 'Recorder' agent logs the action using `read_directory` to confirm the empty state. This multi-agent setup automates entire lifecycle processes without human intervention.

Setup guide

Set up Sirv 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 Sirv tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You expose tools selectively using `tool_filter` when setting up the MCP Server connection. This ensures that only relevant functions, like `search_files`, are available to specific agents.

Yes, that's exactly what it's built for. Agents can operate sequentially or hierarchically, meaning the output of one agent becomes the input task for the next.

The framework excels at handling structured operational data: user records (`list_account_users`), file metadata, and usage metrics. It's designed for systematic analysis.

It does. You can use `MCPServerHTTP` from `crewai.mcp` along with a specific `tool_filter` to control exactly which functions your agents see.

This MCP Server deals heavily with account-level operational data: file metadata, directory listings, and user accounts. It's all about systematic resource management.

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