How to Use the Keywords AI MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK discover tools from the Keywords AI MCP Server?

Your python code registers the server via the MCPServerStreamableHttp class. Once connected, your OpenAI Agents SDK automatically imports all 11 tools like listmodels and getanalytics with zero manual configuration.

Q: Can my OpenAI Agents SDK monitor spending using Keywords AI tools?

Yes, the agent calls getcredits to check your running balance and getusagestats to track volume. This lets your OpenAI Agents SDK make decisions based on real-time financial metrics.

Q: How do I handle model down-time in OpenAI Agents SDK with Keywords AI?

Configure your OpenAI Agents SDK to run checkkeywordsaistatus and listalerts regularly. If a provider goes down, the agent catches the alert and routes subsequent requests to an operational backup model.

Q: Can I filter request logs by model type within the SDK?

Yes, the listrequestsbymodel tool allows you to fetch logs for specific architectures. Your agent uses this to compare latency and output quality directly inside its execution loop.

Track LLM costs and monitor latency across providers directly inside your OpenAI Agents SDK workflows using this 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 Keywords AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Keywords AI to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect LLM requests inside OpenAI Agents SDK

`get_request` acts as the primary tool for your OpenAI Agents SDK to pull exact execution logs for any LLM call. Your agent queries this endpoint to inspect payload details, verify input-output pairs, and catch failing upstream API calls before they break your production run. You can also use `list_requests` to fetch a history of recent operations. This lets your agent analyze past completions, identify patterns in failed prompts, and handle errors dynamically without manual debugging.

Monitor live LLM costs and credit balances

`get_credits` gives your OpenAI Agents SDK direct visibility into your remaining Keywords AI balance to prevent sudden API shutoffs. The agent checks this value before launching long-running batch jobs, pausing execution or alerting your team if funds drop below your safety threshold. Combine this with `get_analytics` to track token spend across different models. This gives your agent the data it needs to switch to cheaper alternatives when budget limits are reached.

Route traffic dynamically using this MCP Server

`list_models` provides your OpenAI Agents SDK with a real-time list of active LLM providers and their current endpoints. Your agent checks this list to discover which models are online, allowing it to route tasks to alternative providers if a primary model goes offline. By calling `list_requests_by_model`, the agent evaluates which specific models are suffering from high latency. It then swaps its target model programmatically, keeping your production pipeline fast and responsive.

Setup guide

Set up Keywords AI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Keywords AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Keywords AI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Keywords AI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Keywords AI Agent",
            instructions="You have access to Keywords AI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your python code registers the server via the `MCPServerStreamableHttp` class. Once connected, your OpenAI Agents SDK automatically imports all 11 tools like `list_models` and `get_analytics` with zero manual configuration.

Yes, the agent calls `get_credits` to check your running balance and `get_usage_stats` to track volume. This lets your OpenAI Agents SDK make decisions based on real-time financial metrics.

Configure your OpenAI Agents SDK to run `check_keywordsai_status` and `list_alerts` regularly. If a provider goes down, the agent catches the alert and routes subsequent requests to an operational backup model.

Yes, the `list_requests_by_model` tool allows you to fetch logs for specific architectures. Your agent uses this to compare latency and output quality directly inside its execution loop.

All LLM request logs, token counts, and API keys are processed inside an ephemeral, zero-trust V8 sandbox. The server never stores your raw credentials, keeping your OpenAI Agents SDK data flow isolated and private.

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