How to Use the Togai (Usage Metering & Pricing) MCP in AutoGen

Q: What financial components does Togai (Usage Metering & Pricing) touch in AutoGen?

The system touches account credentials, pricing plans (createpriceplan), invoices, and usage data. The agents work together to ensure consistency across these records.

Q: What data types are involved when using Togai (Usage Metering & Pricing) and AutoGen?

The core data involves customer identifiers (customerId), financial metrics, usage event schemas, and account balances. These types of structured data make consensus easier to achieve.

Drive consensus-driven billing decisions with AutoGen and 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 Togai (Usage Metering & Pricing) MCP to AutoGen

Create your Vinkius account to connect Togai (Usage Metering & Pricing) to AutoGen 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 Togai (Usage Metering & Pricing) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Facilitate Debate on Entitlement Checks

Agents can debate usage limits. One agent calls `check_entitlement`, while a second agent evaluates the resulting data against predefined rules. They then negotiate whether the action should proceed. This structured discussion ensures that every proposed billing change is vetted by multiple perspectives before execution.

Manage Billing Consensus with AutoGen

When a new customer needs setup, one agent creates the record using `create_customer`, while another calls `create_price_plan`. They must agree on which plan to use. The process is decision-driven. The system requires consensus for critical financial actions like granting credits via `grant_credit`.

Automated Reconciliation of Usage Data

AutoGen can simulate a reconciliation process. Agent A ingests usage events using `ingest_event`. Agent B then calculates the expected cost by checking rate cards (`list_rate_cards`). They compare the totals to flag discrepancies. This robust, multi-step workflow makes billing logic auditable and reliable.

Setup guide

Set up Togai (Usage Metering & Pricing) 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 Togai (Usage Metering & Pricing) 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="Togai (Usage Metering & Pricing)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Togai (Usage Metering & Pricing) 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="Togai (Usage Metering & Pricing)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Togai (Usage Metering & Pricing) 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 Togai. 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 Togai (Usage Metering & Pricing) 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 Togai (Usage Metering & Pricing) MCP in AutoGen

AutoGen allows multiple agents to discuss the implications of a billing action. For instance, one agent might flag an overage detected by `get_metrics`, and another suggests calling `update_account` to fix it.

Yes. You can design a flow where agents collaboratively process data: one ingests the batch events using `ingest_batch_events`, and another validates them against existing entitlements.

The system touches account credentials, pricing plans (`create_price_plan`), invoices, and usage data. The agents work together to ensure consistency across these records.

It's built for that. Because the tools enforce specific operations like `create_account` or `update_customer`, agents must reach a consensus on the exact inputs required, minimizing risk.

The core data involves customer identifiers (`customerId`), financial metrics, usage event schemas, and account balances. These types of structured data make consensus easier to achieve.

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