How to Use the CloudTalk MCP in Pydantic AI

Q: Does this setup support both HTTP and SSE transports for Pydantic AI?

Yes, the MCPToolset class handles connection management over both Streamable HTTP and SSE to communicate with the Vinkius hosting layer using this MCP Server.

Run type-safe CloudTalk operations via MCP with strict Pydantic AI runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CloudTalk MCP to Pydantic AI

Create your Vinkius account to connect CloudTalk 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 CloudTalk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate contact schemas in Pydantic AI before saving

Prevent database corruption by validating contact fields at the runtime level. When your agent runs `create_contact`, the framework ensures the email and phone formats strictly match your Pydantic schemas. If the model attempts to pass an invalid phone format, the tool execution fails loudly before hitting the CloudTalk API. This keeps your CRM data perfectly clean.

Parse CloudTalk call histories with strict type safety

Pull call records using `list_calls` without worrying about missing fields or unexpected null values. The schema returned by the MCP Server is mapped directly to Python types. Your agent can safely filter by agent or direction. Because every field is validated, your downstream analytics code won't throw unexpected runtime type errors.

Safe contact deletion routines

Run sensitive operations like `delete_contact` with absolute certainty. The agent uses `get_contact` first to verify the ID exists and matches the exact record you want to remove. The framework validates the response schema to confirm the deletion was successful. You get clean, typed errors if the API returns an unexpected status code.

Setup guide

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

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

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

Install the MCP dependency, initialize the MCP toolset with your Vinkius HTTP endpoint, and pass it to the `toolsets` argument of your `Agent`.

The framework raises a validation error immediately. This prevents your agent from working with corrupted payloads or hallucinating contact fields.

Yes, the `MCPToolset` class handles connection management over both Streamable HTTP and SSE to communicate with the Vinkius hosting layer using this MCP Server.

Yes. Because the framework is model-agnostic, you can route your validated tool calls to local models or commercial LLM providers.

The validation occurs entirely within your local runtime environment. The raw phone numbers and contact records pass through encrypted TLS channels directly to CloudTalk.

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