How to Use the Sirv MCP in AutoGen

Q: How does Sirv help with file management using AutoGen?

You can model a debate where one agent uses searchfiles to locate an asset, and another debates whether the found metadata is sufficient for action. This simulates expert review.

Q: Can I track billing changes with Sirv and AutoGen?

Yes. You can set up a scenario where one agent calls getbillinginfo to check costs, and another challenges that cost by retrieving usage data via getaccountstats. The debate reveals discrepancies.

Q: What data types can Sirv provide for AutoGen?

Sirv provides everything from user roles (listaccountusers) to complex usage metrics. This variety allows you to build highly realistic, multi-perspective debates between your agents.

Let your agents debate CDN strategy with AutoGen.

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 AutoGen

Create your Vinkius account to connect Sirv to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate deletion risk and necessity.

You can set up two agents: a Security Agent and an Operations Agent. The Ops agent calls `get_file_details` to gather data, and the Security agent debates if calling `delete_file` is safe based on that context. The final decision—the consensus—is what matters here.

Negotiate optimal CDN configuration.

One agent can check current settings using `list_custom_domains`, while another checks user access via `list_account_users`. They debate if a domain needs to be updated because of restricted permissions. The system converges on a single, actionable plan.

Resolve billing discrepancies.

The agents can argue over usage patterns. One might pull `get_account_stats`, while another checks the granular data from `get_detailed_usage`. They debate which metric is more accurate, leading to a final reconciliation report. This simulates a technical review board.

Setup guide

Set up Sirv MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Sirv tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Sirv_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Sirv data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Sirv_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Sirv data")
    print(result.messages[-1].content)

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 AutoGen

You can model a debate where one agent uses `search_files` to locate an asset, and another debates whether the found metadata is sufficient for action. This simulates expert review.

Yes. You can set up a scenario where one agent calls `get_billing_info` to check costs, and another challenges that cost by retrieving usage data via `get_account_stats`. The debate reveals discrepancies.

The agents can perform a 'pre-flight checklist' before calling `delete_file`. One agent verifies the file owner using user lists, while another checks if the file is currently referenced by any active custom domains.

Sirv provides everything from user roles (`list_account_users`) to complex usage metrics. This variety allows you to build highly realistic, multi-perspective debates between your agents.

The server touches billing details and account user lists. When debating, the agents must be prompted to flag any discussion that involves PII or financial numbers, keeping the debate focused on technical outcomes.

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