How to Use the Better Stack MCP in Pydantic AI

Q: How do I load the Better Stack MCP Server into a Pydantic AI agent?

Instantiate MCPToolset with your Vinkius HTTP endpoint URL. Pass this toolset instance inside the toolsets list when defining your Pydantic AI agent.

Q: Does this server support the deprecated MCPServerHTTP class in Pydantic AI?

No, you should use the unified MCPToolset class instead. The older MCPServerHTTP class is deprecated and may cause connection issues with hosted endpoints.

Q: How does Pydantic AI handle schema mismatches with Better Stack tools?

If a tool like liststatuspages returns unexpected fields, Pydantic AI raises a validation error at runtime. This prevents the MCP Server from feeding corrupted data into your critical operations.

Build type-safe incident response workflows by validating all Better Stack API payloads at runtime with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Better Stack MCP to Pydantic AI

Create your Vinkius account to connect Better Stack 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 Better Stack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Incident Validation in Pydantic AI

The `get_incident` tool retrieves the raw JSON timeline payload of an active Better Stack outage. Pydantic AI validates this payload against strict Python schemas before your agent can process the data. If the incident format changes or fields are missing, the framework raises a validation error immediately. This prevents your agent from acting on corrupted or hallucinated operational data.

Strict Monitoring and Heartbeat Checks

The `list_monitors` tool queries your active Better Uptime checks and returns them as typed Python objects. Your agent uses `get_monitor` to inspect specific endpoints, knowing every field matches your codebase definitions. To check background tasks, the agent calls `list_heartbeats` and `get_heartbeat` to verify cron schedules. Because the data is strictly typed, your agent can safely parse timestamps and execution states.

Programmatic Incident Resolution via MCP Server

The `acknowledge_incident` tool lets your agent halt active phone alerts for an ongoing outage. The agent must provide a valid incident ID that conforms to the expected string pattern. Once the system recovers, the agent executes `resolve_incident` to close the alert. Every response from the server is validated, ensuring your on-call team sees accurate updates on their dashboard.

Setup guide

Set up Better Stack 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": {
        "better-stack-1-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Better Stack 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 Better Stack. 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 Better Stack 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 Better Stack MCP in Pydantic AI

Instantiate `MCPToolset` with your Vinkius HTTP endpoint URL. Pass this toolset instance inside the `toolsets` list when defining your Pydantic AI agent.

No, you should use the unified `MCPToolset` class instead. The older `MCPServerHTTP` class is deprecated and may cause connection issues with hosted endpoints.

If a tool like `list_status_pages` returns unexpected fields, Pydantic AI raises a validation error at runtime. This prevents the MCP Server from feeding corrupted data into your critical operations.

The server runs in a managed Vinkius sandbox, so you do not need to host it locally. Your Pydantic AI agent connects securely to the remote endpoint over HTTP or SSE.

All communication between Pydantic AI and the MCP Server happens over encrypted HTTPS channels. Your on-call calendars fetched via `list_on_call` are processed in memory and never stored on external servers.

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