How to Use the SmartChatAI MCP in Pydantic AI

Q: What happens if SmartChatAI and Pydantic AI fail to process a message?

The system won't silently pass bad data. When you use messageaichatbot, the response is validated against your Pydantic models, so failure is explicit and actionable.

Q: How does SmartChatAI and Pydantic AI handle webhook listing?

You use listconfiguredwebhooks to get a list of active webhooks. The output data structure is validated, meaning you'll receive exactly the fields you expect.

Q: Can SmartChatAI and Pydantic AI track chat history?

Yes, call getbotchathistory. This tool retrieves transcripts, and the data is validated on the fly, keeping your audit logs reliable for your agent.

Q: What sources of data can SmartChatAI and Pydantic AI train on?

You handle PDFs (addpdftoknowledgebase), raw text (addtexttoknowledgebase), or websites. The system treats the output from all these tools as strongly typed inputs.

Ensuring Correctness with Pydantic AI and SmartChatAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SmartChatAI MCP to Pydantic AI

Create your Vinkius account to connect SmartChatAI to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SmartChatAI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate Bot Interactions via MCP Server

The `message_ai_chatbot` tool lets you send a message to an agent and receive the reply. Because of your typed validation, if the response format is wrong, it fails loudly—you won't get corrupted data. You can also test connectivity using `check_api_health`. The Pydantic layer validates that this check returns expected status codes before you proceed.

Deep Knowledge Base Ingestion

You train your bots using three tools: `add_pdf_to_knowledge_base`, `add_text_to_knowledge_base`, and `add_website_to_knowledge_base`. Every time data is added, the MCP Server validates that the input format meets expectations. If you're scraping a domain, use `scrape_domain_links` first; the resulting links can then be used to enrich your knowledge base via the website tool.

Manage Agent Configuration

Need an agent or its history? Use `get_chatbot_details` and `list_ai_chatbots`. These tools provide structured, validated data about existing agents. Want to see who's using the system? Call `get_authenticated_user_profile`. The output is a guaranteed-correct object that your agent can rely on.

Setup guide

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

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

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

The system won't silently pass bad data. When you use `message_ai_chatbot`, the response is validated against your Pydantic models, so failure is explicit and actionable.

You use `list_configured_webhooks` to get a list of active webhooks. The output data structure is validated, meaning you'll receive exactly the fields you expect.

Yes, call `get_bot_chat_history`. This tool retrieves transcripts, and the data is validated on the fly, keeping your audit logs reliable for your agent.

You handle PDFs (`add_pdf_to_knowledge_base`), raw text (`add_text_to_knowledge_base`), or websites. The system treats the output from all these tools as strongly typed inputs.

The server touches account profiles, bot configuration details, and conversation transcripts. You'll need to ensure that all these types of sensitive user-generated content are handled securely.

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