How to Use the Readwise MCP in OpenAI Agents SDK

Q: How do I connect the Readwise MCP Server to my OpenAI Agents SDK?

Install the package, then use the MCPServerStreamableHttp class to point to your Vinkius endpoint. Pass this server instance directly into your Agent constructor to auto-discover the 16 available tools.

Q: Can my OpenAI Agents SDK run daily reviews from Readwise?

Yes, the agent calls getdailyreview to pull your scheduled flashcards and highlights. It then processes these items within your custom OpenAI pipeline to trigger spaced repetition tasks.

Q: Does the OpenAI Agents SDK support incremental Readwise exports?

Yes, you configure the agent to call exporthighlights with the updatedAfter parameter. This fetches only the new highlights added since the last run, saving API quota and keeping your OpenAI context window clean.

Q: How do agent handoffs work when searching highlights?

You route queries to a specialized search agent that runs searchhighlights. Once it finds the relevant text, it passes the raw data to a synthesis agent to write the final response.

Feed your OpenAI Agents SDK pipelines with curated highlights and book notes directly from your Readwise library.

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 OpenAI Agents SDK

Create your Vinkius account to connect Readwise to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Sync reading notes directly to OpenAI Agents SDK

`list_highlights` and `export_highlights` feed your OpenAI Agents SDK setup with raw text, notes, and tags. This allows your production OpenAI agents to scan your personal database of Readwise reading materials without manual exports. Your OpenAI Agents SDK pipeline uses these tools to pull specific Readwise passages during a run. The OpenAI dashboard traces every call to the Readwise MCP Server to verify that the agent only accesses the exact books or highlights requested by the user.

Verify and validate Readwise MCP Server actions in OpenAI

`check_readwise_status` verifies your connection to the Readwise API before your OpenAI Agents SDK executes complex multi-agent handoffs. This check prevents downstream failures in your production OpenAI pipelines when Readwise token limits or network issues arise. If an OpenAI agent tries to modify a record, Readwise tools like `update_highlight` and `delete_highlight` run under strict OpenAI guardrails. You define the validation rules in your OpenAI Agents SDK, ensuring the agent never deletes a critical Readwise note without explicit user confirmation.

Search and organize Readwise books via OpenAI Agents SDK

`search_books` and `list_books_by_category` let your OpenAI Agents SDK classify your reading list into structured categories. The OpenAI agent reads the Readwise metadata, filters by source, and groups your literature for targeted processing. By using `list_tags` and `search_highlights`, the OpenAI agent cross-references ideas across different Readwise authors. This turns your static Readwise library into an active knowledge base that your OpenAI Agents SDK query using the MCP protocol.

Setup guide

Set up Readwise MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Readwise tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Readwise tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Readwise tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Readwise Agent",
            instructions="You have access to Readwise tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package, then use the `MCPServerStreamableHttp` class to point to your Vinkius endpoint. Pass this server instance directly into your `Agent` constructor to auto-discover the 16 available tools.

Yes, the agent calls `get_daily_review` to pull your scheduled flashcards and highlights. It then processes these items within your custom OpenAI pipeline to trigger spaced repetition tasks.

Yes, you configure the agent to call `export_highlights` with the `updatedAfter` parameter. This fetches only the new highlights added since the last run, saving API quota and keeping your OpenAI context window clean.

You route queries to a specialized search agent that runs `search_highlights`. Once it finds the relevant text, it passes the raw data to a synthesis agent to write the final response.

The server runs in a secure, ephemeral V8 isolate sandbox that never stores your highlights, book lists, or tags. It acts purely as a stateless bridge between your OpenAI environment and the Readwise API.

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