How to Use the Nylas MCP in Pydantic AI

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

Install the package using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with your Vinkius URL. Pass this toolset into the toolsets parameter of your Agent constructor to expose the email and calendar tools.

Q: Is the MCPServerHTTP transport still supported?

No, MCPServerHTTP is deprecated. You should use the unified MCPToolset("http://...") approach to connect your agent to the externally running Vinkius MCP host.

Q: How does this integration handle the privacy of my contact data?

All contact and calendar records processed by listcontacts and createcontact flow through an ephemeral V8 Isolate sandbox. Vinkius operates on a zero-trust model, meaning your address book data is never stored, cached, or used for model training.

Run type-safe, validated email and calendar operations using Pydantic AI to eliminate silent API failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nylas MCP to Pydantic AI

Create your Vinkius account to connect Nylas 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 Nylas with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe email ingestion with Pydantic AI

`list_messages` returns email data that Pydantic AI validates against strict Python type schemas at runtime. If the underlying email provider returns unexpected metadata, the framework raises a validation error immediately rather than letting corrupted data pass to your model. This strict validation applies to outbound traffic as well when using `send_message` or `list_drafts`. Your agent cannot execute a malformed draft or send an email missing required recipient fields, keeping your communication pipeline clean.

Validated calendar management via Nylas MCP Server

This MCP Server ensures that calendar operations like `create_event` and `list_events` conform to exact schema definitions. Pydantic AI acts as a runtime gatekeeper, verifying that dates, times, and attendee lists match the expected formats before calling the API. If the model attempts to pass an invalid date string to `delete_event` or queries a non-existent calendar ID via `list_calendars`, the framework catches the error. This keeps your scheduling agents running reliably without silent logic failures.

Strict contact directory syncing

`list_contacts` pulls address book records into strongly-typed Pydantic models that your agent can safely inspect. You don't have to worry about missing phone numbers or malformed email strings causing downstream crashes in your application. When adding new people, `create_contact` forces the agent to structure the contact details correctly. The toolset maps the Nylas API requirements directly to Python types, giving you compile-time confidence in your data ingestion.

Setup guide

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

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

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

Install the package using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your Vinkius URL. Pass this toolset into the `toolsets` parameter of your Agent constructor to expose the email and calendar tools.

The framework fails loudly by raising a validation error at runtime instead of letting your agent hallucinate values. This strict behavior ensures your application never processes malformed messages from `list_messages` or `list_folders`.

Yes, because Pydantic AI is model-agnostic, you can pair it with local models or commercial APIs. The framework handles the schema translation, allowing any compatible model to run tools like `list_calendars` or `list_drafts`.

No, `MCPServerHTTP` is deprecated. You should use the unified `MCPToolset("http://...")` approach to connect your agent to the externally running Vinkius MCP host.

All contact and calendar records processed by `list_contacts` and `create_contact` flow through an ephemeral V8 Isolate sandbox. Vinkius operates on a zero-trust model, meaning your address book data is never stored, cached, or used for model training.

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