How to Use the ChatFly MCP in Pydantic AI

Use Pydantic AI and ChatFly to build type-safe, validated conversational agents that handle lead qualification and scheduling.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatFly MCP to Pydantic AI

Create your Vinkius account to connect ChatFly 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 ChatFly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe bot creation for Pydantic AI

Define your bot parameters and call `create_bot` to instantiate them. Pydantic AI validates that your inputs match the required schema before sending them. This approach stops bad data from ever hitting the server. Your bot logic stays robust because the agent forces strict adherence to the data structure.

Strict knowledge management in Pydantic AI

Call `upload_data_source` to populate your bots with specific customer info. Pydantic AI confirms the response structure is correct every time. Query the system with `list_data_sources` to audit your bot's training data. If the API returns unexpected shapes, your agent catches it immediately.

Validated bot updates for Pydantic AI

Update existing bot settings using `update_bot` with complete confidence in your data types. Pydantic AI handles the validation of all updated fields. Use `list_bots` to retrieve your current bot registry. The agent parses the returned list against your models, ensuring consistent runtime behavior.

Setup guide

Set up ChatFly 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": {
        "chatfly-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

The MCPToolset automatically maps tool responses to your models. If the server returns a field that doesn't match your Pydantic definition, the agent raises a clear validation error.

Yes. Since the MCP server is model-agnostic, you can swap your underlying LLM in Pydantic AI without changing how you interact with your bots.

The MCPToolset supports SSE and Streamable HTTP, providing a stable connection. It keeps your agent running even if the network fluctuates during a tool call.

Wrap your tool calls in standard Python try-except blocks. Because Pydantic AI validates the responses, you can easily catch schema mismatches before they cause issues.

Your agent uses an encrypted transport to communicate with the MCP server. We tokenize all credentials, meaning your API keys and customer records remain strictly within the isolated Vinkius runtime.

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