How to Use the Kylas MCP in Pydantic AI

Q: How do I connect this MCP Server to Pydantic AI?

Install the slim package with the MCP extra. Initialize MCPToolset with your Vinkius URL and pass it to your agent's toolsets array.

Q: What happens if Kylas returns bad data to Pydantic AI?

The framework fails loudly. If listdeals returns an unexpected field format, you get a runtime validation error instead of passing bad data to your agent.

Q: Is the old HTTP server class supported here?

No. You must use the unified MCPToolset approach. The older specific server classes are deprecated in current framework versions.

Type-safe Kylas CRM integrations for Pydantic AI agents that demand strict data validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kylas MCP to Pydantic AI

Create your Vinkius account to connect Kylas 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 Kylas with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Kylas leads in your MCP Server

The `get_lead` and `list_leads` tools return raw CRM data that Pydantic AI instantly validates against your schema. If the API returns an unexpected string instead of an integer for a deal value, your application throws a validation error immediately. This stops silent corruption in your sales pipeline. Your agent only acts on verified Indian SMB prospect data, ensuring your downstream Python scripts never process hallucinated fields.

Create contacts with strict typing

The `create_contact` and `create_lead` tools require precise JSON string payloads to write into the CRM. Your agent constructs the payload, but the framework guarantees the structure matches your defined models before the request fires. You swap models without changing the integration. You might run Anthropic for complex reasoning or a local model for speed. The tool execution remains perfectly typed either way.

Type-check tasks via Pydantic AI

The `list_tasks` and `list_deals` tools expose your team's workload to your Python application. When the agent requests the active pipeline, it forces the response into your predefined data structures. You rely on the unified toolset approach for this MCP Server. We host the infrastructure at Vinkius, and your agent connects via a standard HTTP stream to execute the reads.

Setup guide

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

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

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

Install the slim package with the MCP extra. Initialize `MCPToolset` with your Vinkius URL and pass it to your agent's toolsets array.

The framework fails loudly. If `list_deals` returns an unexpected field format, you get a runtime validation error instead of passing bad data to your agent.

Yes. The integration is completely model-agnostic. As long as the model supports tool calling, it can execute `list_contacts` and parse the typed response.

No. You must use the unified `MCPToolset` approach. The older specific server classes are deprecated in current framework versions.

Your deal sizes and prospect names pass through a strict V8 isolate. Vinkius destroys the compute environment the second the HTTP stream closes. No data persists on our servers.

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