Where do I obtain my Readwise Access Token?

You can quickly find or generate your specific access token by logging into your Readwise account and directly visiting `https://readwise.io/access_token`. Copy the alphanumeric token presented there and insert it directly into the prompt required by this integration.

Can the AI add native highlights or upload PDFs to Reader for me?

Currently, the integration server functions on a Read-Only standard format designed specifically to fetch existing knowledge. It fetches metadata or full-text values from highlights, tags, and Reader items, but it doesn't support publishing or updating new sources back to Readwise natively.

Does it also search through to my saved Readwise Reader feed?

Yes. Tools like `list_reader_documents` and `get_reader_document` are designated explicitly for extracting articles or stored reads directly residing inside your connected Readwise Reader account, keeping both typical highlights and Reader data separate but reachable.

Readwise MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: Readwise
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Readwise through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Readwise Assistant",
            instructions=(
                "You help users interact with Readwise. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Readwise"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Readwise MCP Server

Connect your Readwise account directly to your AI agent. Enabling this integration turns your AI into an expert research assistant, capable of instantly scanning your entire timeline of book highlights, article snippets, tweet saves, and personal tags directly from your unified Readwise and Readwise Reader library.

The OpenAI Agents SDK auto-discovers all 6 tools from Readwise through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Readwise, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Highlight Retrieval — Perform searches or bulk retrievals of every snippet, quote, or highlight you've ever saved from your Kindle, Apple Books, and web browsers.
Library Browsing — Ask your AI to list all the books, articles, and sources currently populated in your Readwise database.
Readwise Reader Documents — Full access to list and extract content directly from articles and feeds saved into your Readwise Reader app.
Tag Management Analysis — Retrieve the categorizations and tags you use to organize your knowledge base system.

The Readwise MCP Server exposes 6 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Readwise to OpenAI Agents SDK via MCP

Follow these steps to integrate the Readwise MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 6 tools from Readwise

Why Use OpenAI Agents SDK with the Readwise MCP Server

OpenAI Agents SDK provides unique advantages when paired with Readwise through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Readwise + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Readwise MCP Server delivers measurable value.

Automated workflows: build agents that query Readwise, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Readwise, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Readwise tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Readwise to resolve tickets, look up records, and update statuses without human intervention

Readwise MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect Readwise to OpenAI Agents SDK via MCP:

check_auth_status

Verifies the validity of the Readwise access token

get_reader_document

Retrieves details for a specific Reader document

list_books

Lists all books and sources in Readwise

list_highlights

Lists all highlights from the user's Readwise account

list_reader_documents

Lists documents in the Readwise Reader

list_tags

Lists all tags used in Readwise

Example Prompts for Readwise in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Readwise immediately.

"List the most recent 5 books I highlighted on Readwise."

"Show me the text of the recent document I saved to Reader with the ID 1234."

"Search my highlights for any mentions of 'productivity'."

Troubleshooting Readwise MCP Server with OpenAI Agents SDK

Common issues when connecting Readwise to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Readwise + OpenAI Agents SDK FAQ

Common questions about integrating Readwise MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.