How to Use the AgentFire MCP in Pydantic AI

Q: How do I initialize AgentFire in Pydantic AI?

Install the pydantic-ai-slimmcp package. Create an MCPToolset pointing to the Vinkius HTTP URL and add it to the toolsets array in your Agent definition.

Enforce strict runtime validation for your real estate data by connecting AgentFire to 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 AgentFire MCP to Pydantic AI

Create your Vinkius account to connect AgentFire 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 AgentFire with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate lead data with Pydantic AI

AgentFire acts as an MCP server that turns your CRM operations into strictly typed tool calls. When a local model or Anthropic agent decides to add a prospect, it executes `create_lead` with the mandatory email field. If the LLM hallucinates the email format or forgets it entirely, Pydantic AI catches the mistake immediately and throws a validation error before the bad data reaches your database. Modifying records requires the exact same level of precision. The `update_lead` tool only alters the specific fields you provide in the payload. Pulling existing files via `get_lead` or grabbing the whole batch with `list_leads` ensures your agent always works with structured, predictable dictionaries rather than messy text blobs.

Query the AgentFire MCP Server

Searching for homes demands accurate pricing and location parameters. Your agent runs `search_listings` to filter the market, returning an array of properties that perfectly matches your Pydantic schemas. If a field like square footage comes back as a string instead of an integer, the framework fails loudly rather than silently corrupting your application state. Digging into a specific home is just a matter of calling `get_listing` with the correct ID. You also pull the entire active inventory using `list_listings`. Because Pydantic AI is model-agnostic, you swap out the underlying LLM at any time without rewriting how it interacts with these property endpoints.

Manage contacts and profiles

Getting your brokerage setup correct is the first step in any agent workflow. Firing off `check_agentfire_status` verifies the API is actually awake before your code attempts to process a massive queue of buyers. Failing fast here saves you from dealing with timeouts and retries later in the execution cycle. Your agent needs to know who it works for. Calling `get_profile` loads your specific agent details into the session context. From there, it runs `list_contacts` to pull your entire network into memory, guaranteeing every client interaction relies on verified, type-checked contact data.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package. Create an `MCPToolset` pointing to the Vinkius HTTP URL and add it to the `toolsets` array in your Agent definition.

The framework guarantees runtime correctness. If an agent tries to call `create_lead` without the required email string, the system blocks the execution and returns a validation error immediately.

Yes. You can connect using either Server-Sent Events or Streamable HTTP depending on your infrastructure requirements.

Yes. The toolset remains identical whether you point the framework at OpenAI, Gemini, or a local model running on your machine.

We handle authentication at the edge without storing your credentials. When your agent fetches property listings or buyer contact details, the payload routes through an isolated, single-use environment that evaporates the second the network request completes.

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