How to Use the Axiom MCP in Pydantic AI

Q: How do I configure Axiom with Pydantic AI?

Install pydantic-ai-slimmcp and define an MCPToolset using your Vinkius HTTP endpoint. Attach this toolset to your agent. Note that the older MCPServerHTTP class is deprecated in favor of this unified approach.

Q: How does Pydantic AI handle Axiom query errors?

If a runquery execution returns unexpected schemas or fails entirely, the framework stops execution and raises a loud exception. You get immediate feedback instead of silent data corruption downstream.

Bring strict type validation to your Axiom logs by connecting Pydantic AI to execute guaranteed, hallucination-free APL queries.

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 Pydantic AI

Create your Vinkius account to connect Axiom to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe APL Queries

Silent failures in log analytics ruin incident response. By routing the Axiom MCP Server through Pydantic AI, every single response from `run_query` gets validated against your predefined data models. If the schema changes or the model hallucinates a field, the framework throws a loud validation error immediately. This unified approach means you stop writing defensive parsing logic. You simply install the slim package with MCP extras, instantiate an `MCPToolset` with your endpoint, and let the agent handle the exact data structures you expect.

Deterministic Monitor Creation

Building alerts requires exact parameters for thresholds, time windows, and severity levels. Your agent uses `create_monitor` to provision these rules, ensuring every required field passes strict Pydantic validation before the API call even fires. It links these alerts to external channels using `create_notifier`. Later, if you need an audit of your alerting coverage, the agent runs `list_monitors` and parses the output into a clean, typed Python list for further processing.

Axiom MCP Server Dashboard Control

Visual layouts demand precise JSON structures. When your agent decides to build a new view, it calls `create_dashboard` with validated widget configurations. There is no guessing if the chart type is supported. Need to update an existing graph? The agent fetches the current state via `get_dashboard`, modifies the specific widget parameters, and pushes the changes back through `update_dashboard`. The strict typing guarantees the dashboard will not break upon rendering.

Setup guide

Set up Axiom MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "axiom-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Axiom tools.",
)

result = await agent.run("List recent Axiom transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]` and define an `MCPToolset` using your Vinkius HTTP endpoint. Attach this toolset to your agent. Note that the older `MCPServerHTTP` class is deprecated in favor of this unified approach.

Yes, the agent can structure event payloads and push them using `ingest_data`. Because of the framework's runtime checks, you guarantee that no malformed JSON ever reaches your observability backend.

If a `run_query` execution returns unexpected schemas or fails entirely, the framework stops execution and raises a loud exception. You get immediate feedback instead of silent data corruption downstream.

The framework is completely model-agnostic. You can point the agent at OpenAI, Claude, or a local Ollama instance. They all interact with `list_datasets` and `get_annotation` through the exact same validated interfaces.

Vinkius manages authentication outside your application logic. Your application logs and monitoring metrics pass through an ephemeral, isolated container. We handle the routing securely, meaning your raw telemetry never touches persistent storage on our end.

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