How to Use the ChatGen MCP in Pydantic AI

Q: How do I configure the ChatGen MCP Server with Pydantic AI?

You initialize the connection using MCPToolset with your HTTP endpoint URL. Pass this toolset into the toolsets list when defining your Agent instance to expose the tools.

Q: Can I use ChatGen MCP tools with non-OpenAI models in Pydantic AI?

Yes, Pydantic AI is model-agnostic. You can run tools like listbots and getbot with Gemini, Claude, or local models while maintaining strict type safety.

Q: Does ChatGen support the deprecated MCPServerHTTP wrapper in Pydantic AI?

No, it uses the unified MCPToolset wrapper. This approach simplifies your setup and ensures compatibility with modern SSE and Streamable HTTP transports.

Build type-safe customer support workflows by validating ChatGen data with 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 ChatGen MCP to Pydantic AI

Create your Vinkius account to connect ChatGen 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 ChatGen with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate ChatGen lead data with Pydantic AI

The `get_lead_details` tool fetches raw prospect information and validates it against your Pydantic AI runtime models. If a phone number or email format from `list_leads` is corrupted, the system raises a validation error immediately. This prevents malformed lead data from polluting your CRM. Your agent can confidently process verified fields, knowing that any schema drift in the chat platform will be caught before execution.

Manage bot configurations securely

The `get_bot` tool retrieves active chatbot structures and parses them into strict Python types. If you need to modify a setup, the agent uses `update_bot` to push updates that match your Pydantic schemas exactly. This strict checking ensures your agent never pushes an invalid configuration back to the server. If a field is missing, the execution halts safely instead of breaking your live website chat.

Route conversations using type-safe MCP Server tools

The `list_teams` tool returns your organizational routing targets as typed objects for your Pydantic AI agent. The agent inspects these teams to match incoming inquiries fetched via `list_conversations`. Because the response is fully validated, your routing logic won't fail due to unexpected null values or missing fields. The agent assigns conversations to active teams with complete runtime certainty.

Setup guide

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

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

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

You initialize the connection using `MCPToolset` with your HTTP endpoint URL. Pass this toolset into the `toolsets` list when defining your `Agent` instance to expose the tools.

Yes, Pydantic AI is model-agnostic. You can run tools like `list_bots` and `get_bot` with Gemini, Claude, or local models while maintaining strict type safety.

The framework immediately raises a validation error at runtime. This ensures that tools like `get_lead_details` never inject unvalidated or corrupted data into your agent's decision loop.

No, it uses the unified `MCPToolset` wrapper. This approach simplifies your setup and ensures compatibility with modern SSE and Streamable HTTP transports.

All conversation logs, lead profiles, and bot schemas are isolated in secure V8 environments. The data is only transmitted when your agent explicitly invokes tools like `list_conversations`, keeping your database credentials hidden.

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