How to Use the Incident.io MCP in Pydantic AI

Q: How do I set up the Incident.io MCP Server in Pydantic AI?

You install the MCP dependency using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with your server URL. Pass this toolset directly to your Pydantic AI agent. This unified approach handles the connection and exposes tools like listincidents automatically.

Q: How does Pydantic AI handle the deprecated HTTP transport?

You should use the unified MCPToolset constructor rather than the deprecated MCPServerHTTP class. The toolset automatically negotiates the connection to our managed MCP Server, giving your agent immediate access to tools like listincidentroles.

Run type-safe Incident.io operations with Pydantic AI to guarantee incident data matches your Python models at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Incident.io MCP to Pydantic AI

Create your Vinkius account to connect Incident.io 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 Incident.io with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate incident data structures with Pydantic AI

This MCP Server exposes `get_incident` and `list_incidents` to your Pydantic AI agent, ensuring every incident payload is validated against strict Python types at runtime. If the API returns unexpected fields, Pydantic AI raises a validation error immediately rather than letting your agent process corrupt data. This type safety is critical when automating incident responses where a single wrong field could page the wrong team. By wrapping `get_incident` in a `MCPToolset`, you guarantee that your agent only acts on data that perfectly conforms to your Pydantic schemas.

Parse on-call rosters safely using Pydantic AI

The `list_schedules` and `list_users` tools let your Pydantic AI agent extract active responder rosters and user profiles with absolute structural integrity. The agent parses the schedules to find who is on-call without risking runtime type mismatches. If your Incident.io configuration changes, Pydantic AI will fail loudly on the next call to `list_schedules` if the schema deviates. This immediate feedback prevents your automated paging scripts from failing silently in the middle of a critical outage.

Query custom fields with Pydantic AI MCP Server

This MCP Server uses `list_custom_fields` and `list_catalog_types` to expose your customized organization metadata to Pydantic AI. The agent validates these custom fields against your local Python classes before using them to categorize incidents. Because Pydantic AI is model-agnostic, you can use these validated tools with any LLM provider. The framework handles the conversion of the raw tool outputs from `list_custom_fields` into clean, typed Python objects that your agent can reliably reason about.

Setup guide

Set up Incident.io 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": {
        "incidentio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You install the MCP dependency using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your server URL. Pass this toolset directly to your Pydantic AI agent. This unified approach handles the connection and exposes tools like `list_incidents` automatically.

Pydantic AI will instantly raise a validation error instead of letting your agent hallucinate or crash silently. This ensures that tools like `list_severities` or `list_incident_types` always return data that matches your defined Python types. It is the safest way to run automated incident triage.

Yes, Pydantic AI is completely model-agnostic and works with local models as well as commercial APIs. The framework manages the tool-calling loop for `get_incident` or `list_teams` regardless of which model you choose. Your validation rules remain identical across all models.

You should use the unified `MCPToolset` constructor rather than the deprecated `MCPServerHTTP` class. The toolset automatically negotiates the connection to our managed MCP Server, giving your agent immediate access to tools like `list_incident_roles`.

Your API key is never exposed to the LLM or stored on our platform. The managed MCP Server routes requests to endpoints like `list_users` through an ephemeral, zero-trust V8 sandbox. Authentication is handled via a single secure token, keeping your user directory and incident data completely private.

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