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 Pydantic AI 6 tools — connect in under 2 minutes

Name: Readwise
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Readwise through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

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

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Readwise "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Readwise?"
    )
    print(result.data)

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.

Pydantic AI validates every Readwise tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

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 Pydantic AI 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 Pydantic AI via MCP

Follow these steps to integrate the Readwise MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from Readwise with type-safe schemas

Why Use Pydantic AI with the Readwise MCP Server

Pydantic AI provides unique advantages when paired with Readwise through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Readwise integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Readwise connection logic from agent behavior for testable, maintainable code

Readwise + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Readwise MCP Server delivers measurable value.

Type-safe data pipelines: query Readwise with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Readwise tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Readwise and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Readwise responses and write comprehensive agent tests

Readwise MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect Readwise to Pydantic AI 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 Pydantic AI

Ready-to-use prompts you can give your Pydantic AI 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 Pydantic AI

Common issues when connecting Readwise to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Readwise + Pydantic AI FAQ

Common questions about integrating Readwise MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Readwise MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.