How to Use the Readwise MCP in Pydantic AI

Q: How do I register the Readwise MCP Server with Pydantic AI?

Instantiate the MCPToolset with your Vinkius HTTP endpoint. Pass this toolset instance into your Agent constructor to expose all 16 tools to your model.

Q: Can Pydantic AI validate the output of a Readwise book search?

Yes, when the agent runs searchbooks, the returning list of books is parsed and validated against internal Pydantic models to ensure type safety.

Q: How do I handle missing fields when querying via Pydantic AI?

The framework will raise a validation error if a tool like getbook returns unexpected null values. You can define optional fields in your agent's response models to handle these cases gracefully.

Q: Does Pydantic AI support incremental exports from the Readwise MCP Server?

Yes, you can call exporthighlights using a validated datetime string for the updatedAfter parameter to fetch only new notes safely.

Type-safe extraction of Readwise highlights and book metadata validated at runtime by Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Readwise to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe highlight retrieval with Pydantic AI

`list_highlights` and `get_highlight` return structured JSON containing your Readwise text, notes, and tags directly to Pydantic AI. Pydantic AI validates this Readwise payload against strict Python schemas at runtime, ensuring your agent never processes corrupt or unexpected data structures. If the Readwise API response lacks a required field, the Pydantic AI framework raises a validation error immediately. This strict behavior prevents silent failures and ensures your Readwise database syncs in Pydantic AI remain clean.

Validate Readwise MCP Server review queues in Pydantic AI

`get_daily_review` and `list_reviews` pull your active Readwise spaced repetition queue into your Pydantic AI application. Pydantic AI parses these Readwise reviews into strongly-typed models, letting you write clean code that handles dates, book IDs, and text blocks safely. The Pydantic AI agent uses these validated Readwise models to serve daily flashcards. Because the Readwise data matches your schemas exactly, you can run complex local logic over the MCP stream in Pydantic AI without worrying about missing attributes.

Manage Readwise books and tags in Pydantic AI

`list_books` and `list_tags` allow your Pydantic AI agent to discover your Readwise reading sources and taxonomy. Pydantic AI ensures that every Readwise book category, source name, and tag string is validated before it reaches your application logic. When creating or modifying data, Readwise tools like `create_highlight` and `update_highlight` accept strict Pydantic AI input models. This guarantees that your Pydantic AI agent sends correctly formatted payloads back to the Readwise API every single time.

Setup guide

Set up Readwise MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "readwise-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Readwise tools.",
)

result = await agent.run("List recent Readwise transactions")
print(result.output)

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 Pydantic AI

Instantiate the `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset instance into your `Agent` constructor to expose all 16 tools to your model.

Yes, when the agent runs `search_books`, the returning list of books is parsed and validated against internal Pydantic models to ensure type safety.

The framework will raise a validation error if a tool like `get_book` returns unexpected null values. You can define optional fields in your agent's response models to handle these cases gracefully.

Yes, you can call `export_highlights` using a validated datetime string for the `updatedAfter` parameter to fetch only new notes safely.

Your token is injected securely into the Vinkius gateway and never exposed to the client. The Pydantic AI agent only sees the validated JSON payloads representing your books and highlights sent over MCP.

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