How to Use the CHATFLY MCP in Pydantic AI

Q: How do I configure CHATFLY with Pydantic AI?

Install the pydantic-ai-slimmcp package. Create an MCPToolset pointing to your Vinkius URL and pass it into your Agent's toolsets parameter.

Q: Why use Pydantic AI for CHATFLY instead of standard Python requests?

Runtime validation catches errors instantly. If listchatflybots returns an unexpected data structure, the framework throws a validation error before your agent makes a bad decision.

Q: Can Pydantic AI read my CHATFLY support conversations?

Yes. The agent uses getconversationhistory to retrieve the messages. You can define a Pydantic model to strictly parse the user and bot message pairs from that output.

Force strict type validation on your CHATFLY bot configurations and support conversations using 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 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 CHATFLY bot audits

Type-safe audits of your CHATFLY bots prevent silent failures in customer support automation. When your agent pulls active instances via `list_chatfly_bots`, Pydantic AI strictly validates the returned JSON from this MCP integration. If the API changes or drops a field, the agent fails loudly instead of hallucinating a response. You get the exact same guarantee when inspecting specific setups. The agent runs `get_chatbot_details` and maps the output directly to your internal data models. Bad data never makes it into your downstream metrics.

Validated knowledge base management

Validated knowledge base management ensures your bots only train on approved files. Your agent can monitor the exact state of your training data by calling `list_uploaded_documents`. It checks those results against your quota limits pulled from `get_chatfly_account_info`. If the agent decides the bot needs a refresh, it fires `trigger_bot_training`. Because you defined the expected outcome in Pydantic, you know immediately if the training job started successfully or if the CHATFLY API threw an error.

Pydantic AI chat history via MCP Server

Extracting support data requires precise formatting of your chat histories. Your agent grabs recent interaction IDs using `list_fly_conversations`. It then iterates through those threads, pulling the exact message logs with `get_conversation_history`. You can also build automated testing routines. The agent fires test prompts using `send_bot_message` and forces the LLM to evaluate the response against a strict schema, ensuring your bots stay accurate.

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-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

Install the pydantic-ai-slim[mcp] package. Create an MCPToolset pointing to your Vinkius URL and pass it into your Agent's toolsets parameter.

Runtime validation catches errors instantly. If `list_chatfly_bots` returns an unexpected data structure, the framework throws a validation error before your agent makes a bad decision.

Yes. The agent uses `get_conversation_history` to retrieve the messages. You can define a Pydantic model to strictly parse the user and bot message pairs from that output.

The framework is totally model-agnostic. You can run Llama locally and still connect to Vinkius to manage your chatbots and training queues.

This integration reads proprietary training documents and private customer chat logs. We handle authentication at the network edge, passing your requests through a stateless sandbox that retains zero memory of your data.

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