How to Use the Evernote MCP in Pydantic AI

Q: How do I configure this Evernote MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp. Use the unified MCPToolset class with your server URL. Pass that toolset to your Agent to get started.

Connect this Evernote MCP server to Pydantic AI. Manage notebooks and tags with strict runtime validation for your agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evernote MCP to Pydantic AI

Create your Vinkius account to connect Evernote 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 Evernote with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Bring type-safety to Evernote with Pydantic AI.

The `get_user` tool pulls your Evernote profile and quota information directly into a validated Pydantic model. If the API returns a missing field, your agent fails loudly. You never have to worry about silent data corruption creeping into your workflow. The `get_notebook` tool fetches metadata by GUID so your agent knows exactly what fields to expect. This strictness applies everywhere. You get absolute correctness when mapping out your workspace.

Read and write with absolute precision.

The `get_note` tool fetches the exact ENML content of any document. Your agent parses this markup natively, ensuring that tables, lists, and text formatting are handled correctly before any processing happens. The `update_note` tool modifies a specific document and increments the updateSequenceNum. Writing back is highly deliberate. If the agent needs to start fresh, `create_note` pushes a brand new file that syncs across all clients instantly.

Map and query your entire archive.

The `search_notes` tool executes complex queries using Evernote's native syntax. Your agent doesn't just guess where things are; it runs a precise search and validates the returned metadata against your schemas. The `list_tags` tool shows the agent exactly how you categorize information. It pairs this with `list_notebooks` to discover available folders, then uses `list_notes` to pull structured batches of 50 items at a time.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Use the unified `MCPToolset` class with your server URL. Pass that toolset to your Agent to get started.

The MCP server handles the initial tool execution, returning the raw ENML string. You can write custom Pydantic validators on your end to ensure the agent parses that markup correctly.

The tool execution will fail and return an error to the agent. Because Pydantic AI enforces strict response handling, the agent will catch the error immediately rather than hallucinating a fake document.

The tool increments the updateSequenceNum on a successful write. If another client modified the document first, the Evernote API will reject the update, and your agent will receive a clear failure message.

The MCP server processes your tags, notebook GUIDs, and note titles inside a stateless V8 Isolate. Vinkius handles the network transport securely, meaning your workspace metadata flows strictly to your local Pydantic models and is never stored on disk.

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