How to Use the Readwise MCP in AutoGen

Q: How do I register Readwise tools with an AutoGen assistant?

Install autogen-extmcp and use the adapter to fetch the tools from the server URL. Pass the tools list to your AssistantAgent constructor, and the MCP schema conversion happens automatically.

Q: Can I run a multi-agent debate over a specific book found via Readwise?

Yes. One agent can call getbook to pull the metadata and chapters, while other agents analyze the content. This lets them debate the book's core themes using verified source details.

Let your AutoGen agents debate and synthesize your Readwise library to extract deep insights.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Readwise MCP to AutoGen

Create your Vinkius account to connect Readwise to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Readwise with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Consensus-driven research with AutoGen and Readwise

Set up a multi-agent debate where one agent pulls data using `list_highlights` and another critiques the source quality. By separating the retrieval and analysis roles, you get much sharper syntheses of your reading material. The retrieval agent can run `search_highlights` to find relevant quotes, while the writer agent drafts a summary. They negotiate back and forth until they agree the summary matches the source books accurately.

Collaborative library curation via AutoGen

You can assign one agent to audit your tags while another handles categorization. Using `list_tags` and `list_books` via MCP, the audit agent flags inconsistent labels. The editing agent then uses `update_highlight` to fix them. This collaborative loop runs autonomously in the background. Because AutoGen handles multi-agent communication, the agents can resolve conflicts on tag naming conventions before writing changes back to Readwise.

Automated review moderation using an MCP Server

Run a daily review pipeline where agents discuss your active cards. An agent calls `get_daily_review` to fetch the queue, then discusses with a tutor agent how to best apply those concepts to your current projects. If a review card is no longer useful, the performance agent can suggest calling `delete_highlight` to prune the queue. They only execute the tool once both agents agree the card has served its purpose.

Setup guide

Set up Readwise 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 Readwise 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="Readwise_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Readwise 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="Readwise_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Readwise 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 Readwise. 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 Readwise 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 Readwise MCP in AutoGen

Install `autogen-ext[mcp]` and use the adapter to fetch the tools from the server URL. Pass the tools list to your `AssistantAgent` constructor, and the MCP schema conversion happens automatically.

Yes. You can set up a writer agent and a critic agent. The writer uses `create_highlight` or `update_highlight` to organize notes, while the critic checks if the tags align with your library's structure.

The agents can coordinate their tool calls. Instead of hammering the API, they can use `export_highlights` with timestamp filters over MCP to fetch updates incrementally, keeping API usage within safe bounds.

Yes. One agent can call `get_book` to pull the metadata and chapters, while other agents analyze the content. This lets them debate the book's core themes using verified source details.

The server runs in a secure, zero-trust V8 sandbox. Write operations like `delete_highlight` or `update_highlight` are only executed when explicitly triggered by your agents. Your personal reading data is never shared.

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