How to Use the FireHydrant MCP in Pydantic AI

Q: How do I configure the FireHydrant toolset in Pydantic AI?

Use the MCPToolset class to point to your hosted endpoint on Vinkius. Pass the toolset directly to your Agent constructor to give your model access to the 12 MCP tools.

FireHydrant incident response with Pydantic AI guarantees type-safe updates, stopping broken agent actions before they hit production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FireHydrant MCP to Pydantic AI

Create your Vinkius account to connect FireHydrant 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 FireHydrant with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate incident updates with Pydantic AI

The `update_incident` tool enforces strict schemas on every status change, ensuring your agent never sends malformed payloads to your incident tracker. Pydantic AI validates the model's output at runtime, catching formatting errors before they touch your live environment. If your agent attempts to resolve an incident with missing metadata, the framework raises an explicit validation error. This prevents silent failures and keeps your incident timeline clean and accurate.

Safely query services via the MCP Server

The `list_services` tool returns your entire service catalog as structured data that the model parses into typed Python objects. Your agent can safely inspect service dependencies without risking runtime key errors or unexpected null values. This MCP Server integration works across any LLM you choose, from OpenAI to local models. The validation layer remains constant, meaning you get the same structural guarantees regardless of the underlying model's reasoning quirks.

Enforce strict schemas on post-mortem data

The `list_retrospectives` tool extracts historical incident data, which your agent parses into structured summaries for your post-mortem documents. By validating the API response against strict schemas, you guarantee that every generated report contains the required impact metrics. You can also run `add_incident_note` to append verified timeline events. The framework ensures that notes contain valid markdown and follow your organization's exact formatting rules.

Setup guide

Set up FireHydrant 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": {
        "firehydrant-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the `MCPToolset` class to point to your hosted endpoint on Vinkius. Pass the toolset directly to your `Agent` constructor to give your model access to the 12 MCP tools.

The framework immediately raises a validation error instead of passing bad data to the model. This guarantees that your agent never acts on corrupted service or incident schemas.

Yes. Because the framework is model-agnostic, you can connect the server to local models or commercial APIs while maintaining the exact same MCP validation rules.

The server supports both Streamable HTTP and SSE transports. We recommend using the unified `MCPToolset` class rather than deprecated transport-specific classes.

Yes. The server only processes change events and retrospective data within secure, ephemeral V8 isolates. Vinkius secures the transport layer, ensuring that your system change logs are never cached or exposed.

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