How to Use the Chanty MCP in Pydantic AI

Q: How do I initialize the Chanty MCP Server toolset in Pydantic AI?

Instantiate MCPToolset with your Vinkius HTTP URL. Pass this toolset object directly into your agent's toolsets parameter during initialization.

Q: Is the old MCPServerHTTP class still supported for Chanty?

No, that class is deprecated. You should use the unified MCPToolset class for all HTTP and SSE transport connections.

Enforce runtime type-safety on your Chanty automations 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 Chanty MCP to Pydantic AI

Create your Vinkius account to connect Chanty 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 Chanty with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe message dispatching

Your agent uses the `send_message` tool to guarantee all outgoing payloads match strict schemas. The agent dispatches payloads, validating the response format at runtime. Catching errors early prevents broken JSON or unexpected null fields from crashing your production pipeline. If Chanty returns an unexpected format, your Pydantic AI agent catches it instantly.

Validated directory mapping

Pulling data with the `list_members` tool returns clean, typed lists of your team members. The framework validates the returned user IDs and profile structures against your defined Pydantic models. You avoid silent data corruption in your internal directory syncs. The agent guarantees that every member record matches your application's expected types.

Safe conversation cleanup using MCP Server tools

Executing the `delete_conversation` tool safely removes outdated channels without risking accidental deletions. The agent checks the channel status first using `list_conversations` to verify it meets your cleanup criteria. Using this MCP Server ensures that structural changes to your chat workspace are fully validated. You get compile-time and runtime safety for every channel modification.

Setup guide

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

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

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

Instantiate `MCPToolset` with your Vinkius HTTP URL. Pass this toolset object directly into your agent's `toolsets` parameter during initialization.

No, that class is deprecated. You should use the unified `MCPToolset` class for all HTTP and SSE transport connections.

The framework raises a validation error immediately if the server response deviates from the expected schema. This prevents corrupt data from propagating through your system.

Yes, this framework is model-agnostic. You can run your Chanty automations using Anthropic, Gemini, or even local models.

Vinkius acts as a secure, ephemeral gateway that never stores your credentials. All validation occurs in a sandboxed runtime, keeping your conversation tokens completely isolated.

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