How to Use the Keywords AI MCP in AutoGen

Q: How do AutoGen agents use Keywords AI to manage costs?

The agents use getcredits and getusagestats to verify if a task is within budget. If it isn't, they negotiate a cheaper model or pause the task.

Q: Can Keywords AI help my AutoGen team troubleshoot errors?

Yes. Your debugging agent can call getrequest for failed logs and present the details to the other agents to diagnose the problem.

Q: Is it simple to connect Keywords AI to an AutoGen project?

It is. Use the mcpservertools adapter to load the endpoints, then inject them into your AssistantAgent constructor.

Let your AutoGen agents debate and optimize your LLM stack using live performance data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keywords AI MCP to AutoGen

Create your Vinkius account to connect Keywords AI 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 Keywords AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-based cost management

Assign a budget agent to call `get_credits` and debate with your primary agent about model selection. They negotiate costs before a single token is generated. It prevents runaway spending by requiring agents to agree on the model's cost profile. The logic is handled through iterative discussion between your specialized agents.

Performance-driven agent negotiation

Your performance agent can use `list_requests_by_model` to argue for or against specific providers based on real-time latency data. It ensures your agents choose the fastest route. This creates a system where agents self-correct based on live metrics. They don't just execute; they evaluate the health of the Keywords AI gateway before starting a task.

Real-time alert resolution

When `list_alerts` reports a failure, your agents can debate the best fallback strategy. They decide collectively which model to switch to, keeping your pipeline running. It turns monitoring into an active conversation. Your agents handle the troubleshooting, using the MCP tools as their source of evidence during the debate.

Setup guide

Set up Keywords AI 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 Keywords AI 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="Keywords AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The agents use `get_credits` and `get_usage_stats` to verify if a task is within budget. If it isn't, they negotiate a cheaper model or pause the task.

Yes. Your debugging agent can call `get_request` for failed logs and present the details to the other agents to diagnose the problem.

It does. With eleven distinct tools, the agents have access to full analytics, model lists, and status checks to support their arguments.

It is. Use the `mcp_server_tools` adapter to load the endpoints, then inject them into your `AssistantAgent` constructor.

All communication between your agents and the server is handled via secure, authenticated tokens. The data retrieved is limited to the telemetry you choose to share.

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