How to Use the Axiom MCP in OpenAI Agents SDK

Q: How do I connect Axiom to OpenAI Agents SDK?

Install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass that into the mcpservers list when constructing your agent. Use an async context manager to handle the connection lifecycle safely.

Q: Can OpenAI Agents SDK create new Axiom datasets?

Yes, the agent has full access to the createdataset tool. It can spin up isolated storage for specific application logs on demand. You can also enforce guardrails to require human approval before creation.

Q: Does the Axiom MCP Server support APL queries in OpenAI Agents SDK?

The runquery tool accepts raw APL syntax. Your agent will write and execute the query, then parse the JSON response. If the query fails, the agent reads the error and rewrites the syntax automatically.

Build production-grade observability agents using OpenAI Agents SDK to query Axiom logs and manage monitors with strict execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Axiom MCP to OpenAI Agents SDK

Create your Vinkius account to connect Axiom 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 Axiom with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run APL Queries via OpenAI Agents SDK

Your deployment relies on fast log analysis when things break. Passing the Axiom MCP Server to your agent lets it execute `run_query` directly against your telemetry data. The built-in OpenAI guardrails validate every APL syntax structure before the agent actually sends the payload. Tracing comes natively with this framework. When the agent uses `ingest_data` to push new events, you see the entire chain of thought and execution in the OpenAI dashboard. Set `cacheToolsList=True` during initialization to skip redundant tool discovery and keep response times low.

Configure Alerting Pipelines

Setting up observability infrastructure usually means clicking through web interfaces or writing Terraform. Now your specialized agent can handle it by calling `create_monitor` and `create_notifier` based on natural language requirements. Handoffs work perfectly here. One agent analyzes error rates using `get_dataset`, then passes context to an infrastructure agent that builds the actual alerts. If a threshold needs adjusting later, the system simply calls `update_monitor` without human intervention.

Dynamic Dashboard Generation

Visualizing metrics takes time that your on-call engineers do not have during an incident. The agent can evaluate an ongoing outage and immediately use `create_dashboard` to group relevant logs into a single view. Once the incident resolves, cleanup is just as automatic. The agent calls `delete_dashboard` to remove temporary views, keeping your Axiom workspace clean. This happens entirely within the safety constraints you defined in the agent's system prompt.

Setup guide

Set up Axiom 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 Axiom tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Axiom 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="Axiom Agent",
            instructions="You have access to Axiom 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 Axiom. 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 Axiom 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 Axiom MCP in OpenAI Agents SDK

Install `openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass that into the `mcp_servers` list when constructing your agent. Use an async context manager to handle the connection lifecycle safely.

Yes, the agent has full access to the `create_dataset` tool. It can spin up isolated storage for specific application logs on demand. You can also enforce guardrails to require human approval before creation.

The `run_query` tool accepts raw APL syntax. Your agent will write and execute the query, then parse the JSON response. If the query fails, the agent reads the error and rewrites the syntax automatically.

Give your agent a prompt to audit current alerts, and it will trigger `list_monitors`. It can then iterate through the results and use `update_monitor` if any thresholds violate your current alerting policies.

Vinkius runs the Axiom integration inside an ephemeral V8 Isolate sandbox. Your raw telemetry logs and APL query results only exist in memory during the request. The sandbox terminates immediately after the agent finishes its task, leaving zero residual data behind.

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