How to Use the CometAPI MCP in AutoGen

Q: How do AutoGen agents debate model choices using CometAPI?

One agent calls getpricinginformation while another calls listavailableaimodels. They compare costs and capabilities in a group chat to choose the optimal model before executing createaichatcompletion.

Q: Can I use CometAPI to convert AutoGen agent conversations into speech?

Yes, you can configure an agent to call converttexttospeech on the final group consensus message. This generates an audio file of the conversation's output.

Q: How does the CometAPI MCP Server handle tool schemas in AutoGen?

The McpToolAdapter automatically translates the server's tool definitions into the format AutoGen expects. You don't have to manually write JSON schemas for your agents.

Q: How is my account usage data secured when AutoGen agents call CometAPI?

Your usage metrics and profile details retrieved by getapiusagestatistics are encrypted in transit using TLS 1.3. The Vinkius gateway handles authentication, so your raw API credentials are never exposed to the individual agents.

Run multi-agent debates in AutoGen to negotiate model selection, image generation, and cost optimization.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CometAPI MCP to AutoGen

Create your Vinkius account to connect CometAPI 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 CometAPI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent negotiations over model selection

`list_available_ai_models` provides the raw data your AutoGen agents need to debate which model fits a specific task. Budget constraints are weighed against quality metrics as agents negotiate the best path forward.

Collaborate on image and audio generation tasks

`generate_ai_image` lets your design agent generate visual assets based on prompts written by a copywriter agent. Critics review the image and suggest prompt adjustments until the team reaches consensus.

Optimize group chat budgets with this MCP Server

`get_api_usage_statistics` gives your coordinator agent a live look at the group's total spend. Coordinator agents step in to restrict budgets if one agent calls expensive models too frequently.

Setup guide

Set up CometAPI 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 CometAPI 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="CometAPI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CometAPI 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="CometAPI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CometAPI 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 CometAPI. 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 CometAPI 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 CometAPI MCP in AutoGen

One agent calls `get_pricing_information` while another calls `list_available_ai_models`. They compare costs and capabilities in a group chat to choose the optimal model before executing `create_ai_chat_completion`.

Yes, you can configure an agent to call `convert_text_to_speech` on the final group consensus message. This generates an audio file of the conversation's output.

The `McpToolAdapter` automatically translates the server's tool definitions into the format AutoGen expects. You don't have to manually write JSON schemas for your agents.

Use the Streamable HTTP transport and configure the MCP client with your Vinkius endpoint token. This provides a stable, secure connection for distributed agents running in different environments.

Your usage metrics and profile details retrieved by `get_api_usage_statistics` are encrypted in transit using TLS 1.3. The Vinkius gateway handles authentication, so your raw API credentials are never exposed to the individual agents.

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