How to Use the Evernote MCP in AutoGen

Q: How do I configure Evernote for AutoGen?

Use mcpservertools with StreamableHttpServerParams. Pass the resulting tool list into your AssistantAgent constructor.

Q: Will AutoGen overwrite my existing Evernote files?

Only if an agent explicitly calls updatenote with the correct GUID. You can restrict write access by filtering the allowed tools.

Q: How do agents find specific notes in Evernote?

They use searchnotes with standard query syntax. The MCP server returns metadata, and they follow up with getnote for the full text.

Give your AutoGen agents the ability to draft, debate, and publish Evernote documents autonomously.

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 AutoGen

Create your Vinkius account to connect Evernote to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Draft and revise documents natively

The `create_note` tool lets an AutoGen agent draft a document and push it straight to your account. The note syncs immediately, making it visible on your phone or desktop. You can assign one agent to write the draft and another to review it. If the reviewer finds errors, it calls `update_note` to push corrections, incrementing the update sequence number natively.

Monitor quotas via the MCP Server

The `get_user` tool pulls profile information and quota limits for the authenticated account. A supervisor agent monitors this data to ensure the team does not hit API rate limits. If the quota looks tight, the supervisor can instruct the worker agents to slow down their requests. This keeps long-running debates from crashing the MCP Server connection.

Debate taxonomy and structure

The `list_tags` tool retrieves your existing organization system. Agents debate which tags apply to a new document before attaching them. If a dedicated space is needed for a new project, an agent fires `create_notebook`. It grabs the new notebook GUID and shares it with the rest of the swarm so they know where to store their work.

Setup guide

Set up Evernote MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Evernote tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Evernote_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Evernote data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Evernote_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Evernote data")
    print(result.messages[-1].content)

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 AutoGen

Use mcp_server_tools with StreamableHttpServerParams. Pass the resulting tool list into your AssistantAgent constructor.

Yes. Once you register the tools, any agent in the conversation can call them to read or write notes.

Only if an agent explicitly calls update_note with the correct GUID. You can restrict write access by filtering the allowed tools.

They use search_notes with standard query syntax. The MCP server returns metadata, and they follow up with get_note for the full text.

The server handles your structural metadata and text content. Authentication is completely decoupled from the runtime, meaning your developer tokens never touch the client application directly.

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