Bring Reading
to Pydantic AI
Learn how to connect Readwise to Pydantic AI and start using 16 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Readwise MCP Server?
Transform how your organization interacts with reading material by giving your AI agent full control over your Readwise library. With 16 tools covering full highlight CRUD, book search by source and category, tag management, and daily review access, your agents can retrieve specific passages, create annotations, and help you retain knowledge.
What you can do
- Browse books by source or category
- Full CRUD for highlights, notes, and tags
- Access daily spaced repetition reviews
- Export all data incrementally for backup or analysis
How it works
1. Subscribe to this server 2. Enter your Readwise API Token (found in your account settings) 3. Start managing your reading library directly from Claude, Cursor, or any MCP clientWho is it for?
Ideal for researchers, students, and professionals needing instant, conversational access to their curated knowledge base.Built-in capabilities (16)
Verify connectivity
Create a highlight
Delete a highlight
Supports incremental export with updatedAfter filter. Export highlights
Get book details
Get daily review
Get highlight details
List all books
List books by category
List books by source
Returns text, note, location, and tags. List highlights
List review queue
List all tags
Search books
Search highlights
Update a highlight
Why Pydantic AI?
Pydantic AI validates every Readwise tool response against typed schemas, catching data inconsistencies at build time. Connect 16 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.
- —
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 in Pydantic AI
Readwise and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Readwise to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Readwise in Pydantic AI
The Readwise 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. All 16 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Readwise for Pydantic AI
Every tool call from Pydantic AI to the Readwise MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
What can I do with the Readwise connector?
You can list, search, create, update, and delete highlights, browse books by source or category, manage tags, access your daily spaced repetition review, and export all data incrementally for analysis or backup.
How does the daily review feature work?
The daily review tool retrieves highlights selected by Readwise's spaced repetition algorithm, helping your AI agent surface the most important passages at the optimal retention interval.
Can I filter books by where they came from?
Yes, you can filter by source (Kindle, Instapaper, Pocket, web, Apple Books) or by category (books, articles, tweets, podcasts) to quickly find the content you need.
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.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai