Bring Telemetry
to OpenAI Agents SDK
Learn how to connect Axiom to OpenAI Agents SDK and start using 31 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Axiom MCP Server?
Connect your Axiom account to any AI agent to streamline your observability and log management workflows through natural conversation.
What you can do
- Data Ingestion & Querying — Ingest JSON, NDJSON, or CSV data and run complex Axiom Processing Language (APL) queries to analyze logs in real-time.
- Dataset Management — List, create, and update datasets to organize your telemetry and infrastructure data efficiently.
- Monitoring & Alerts — Manage monitors and notifiers to stay informed about system performance, errors, and anomalies.
- Dashboards & Annotations — Access dashboards and create annotations to visualize trends and mark significant system events.
- Organization Insights — Retrieve user information, API tokens, and organization details to maintain secure and authorized access.
How it works
- Subscribe to this server
- Enter your Axiom API Token and optional Organization ID
- Start analyzing your logs and managing infrastructure from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps & SREs — instantly query logs for errors, check monitor statuses, and manage alerts without leaving the terminal or chat.
- Software Engineers — debug production issues by running APL queries directly from the code editor to find specific trace IDs or logs.
- Data Analysts — ingest and analyze large datasets using Axiom's powerful processing language through simple natural language prompts.
Built-in capabilities (31)
Create a new annotation
Create a new dashboard
Create a new dataset
Create a new monitor
Create a new notifier
Delete an annotation
Delete a dashboard
Delete a dataset
Delete a monitor
Delete a notifier
Retrieve a specific annotation by ID
Retrieve a specific dashboard by UID
Retrieve a specific dataset by ID
Retrieve a specific monitor by ID
Retrieve a specific notifier by ID
Retrieve an organization by ID
Retrieve a specific user by ID
Ingest data into an Axiom dataset
List all annotations
List all dashboards
List all datasets
List all monitors
List all notifiers
List all API tokens
List all users
Run an APL query against Axiom data
Update an existing annotation
Update an existing dashboard
Update an existing dataset
Update an existing monitor
Update an existing notifier
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 31 tools from Axiom through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Axiom, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Axiom in OpenAI Agents SDK
Axiom and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Axiom to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Axiom in OpenAI Agents SDK
The Axiom MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 31 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Axiom for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Axiom MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I run complex log analysis using Axiom Processing Language (APL)?
Yes! Use the run_query tool to execute any APL string. You can specify start_time and end_time to filter your data and get precise analytical results directly in the chat.
How do I send new log data to my Axiom datasets?
You can use the ingest_data tool. Simply provide the dataset_name, the data payload, and the content_type (JSON, NDJSON, or CSV) to stream data into your Axiom account.
Is it possible to manage system monitors and alerts through this integration?
Absolutely. You have access to a full suite of tools including list_monitors, create_monitor, and update_monitor to configure threshold or anomaly detection alerts based on your APL queries.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Walmart Orders & Fulfillment
8 toolsSecurely process e-commerce orders, manage fulfillment logistics, and handle customer returns.
OpenFEC (Federal Election Commission)
21 toolsAccess real-time federal campaign finance data — search candidates, track committee filings, and analyze election financial totals directly.
The Odds API
3 toolsUniversal sports betting intelligence — get real-time odds, scores, and sports data via AI.
EIA State Energy — U.S. Regional Energy Data
3 toolsState-level energy data spanning 65 years: production, consumption, prices, and expenditures for ALL energy sources by state and sector (SEDS), the comprehensive Monthly Energy Review (MER), and nuclear reactor outage tracking.