How to Use the Readwise MCP in LlamaIndex

Q: How do I load Readwise data into a LlamaIndex vector store?

Use the llama-index-tools-mcp package to initialize the client. Call totoollistasync to get the tools, then let your agent use exporthighlights over the MCP connection to pull data and feed it to your indexer.

Q: Can a LlamaIndex agent search my Readwise books by source?

Yes. The agent can invoke listbooksbysource to filter your library. This allows the agent to build sub-indices specifically for articles, physical books, or tweets.

Q: How do I handle large Readwise libraries without hitting LlamaIndex token limits?

Use exporthighlights with the incremental filter to only fetch recent updates. This avoids loading your entire reading history into memory at once, keeping index updates fast and lightweight.

Q: Does this MCP Server support daily reviews in LlamaIndex?

Yes. The getdailyreview tool pulls your active review cards. Your agent can parse these cards, run semantic lookups, and present them with extra context from your vector store.

Index your Readwise library into LlamaIndex vector stores for hyper-accurate semantic search.

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 LlamaIndex

Create your Vinkius account to connect Readwise to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Turn Readwise highlights into LlamaIndex vector nodes

Stop relying on keyword search to find old notes. This MCP Server lets LlamaIndex pull raw text using `list_highlights` and turn those snippets into vector embeddings. Your agent can then perform semantic queries across your entire reading history. By using `get_book` alongside the highlights, the index retains crucial metadata like authors and categories. This means your RAG pipeline can filter search results by specific books before generating answers.

Grounding agent responses in real reading data

Prevent your agent from hallucinating facts by grounding its context in your actual library. The agent runs `search_highlights` over the MCP to verify claims against your saved quotes. It ensures that the generated output matches what you actually read. You can also use `list_books_by_category` to limit the search space to relevant topics. If you are writing about biology, the agent only queries books in that category, saving compute and improving accuracy.

Active catalog curation through LlamaIndex tools

Your agent can clean up your reading index as it reads. If it finds a duplicate or poorly formatted note, it calls `update_highlight` or `delete_highlight` to fix it. This keeps your physical database in sync with your vector store. Use `list_tags` to let the agent organize your notes programmatically. It can scan highlight text, determine the main themes, and apply tags without you clicking through the Readwise web app.

Setup guide

Set up Readwise MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Readwise MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Readwise tools.",
)
response = await agent.run("List recent Readwise data")

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 LlamaIndex

Use the `llama-index-tools-mcp` package to initialize the client. Call `to_tool_list_async` to get the tools, then let your agent use `export_highlights` over the MCP connection to pull data and feed it to your indexer.

Yes. The agent can invoke `list_books_by_source` to filter your library. This allows the agent to build sub-indices specifically for articles, physical books, or tweets.

Use `export_highlights` with the incremental filter to only fetch recent updates. This avoids loading your entire reading history into memory at once, keeping index updates fast and lightweight.

Yes. The `get_daily_review` tool pulls your active review cards. Your agent can parse these cards, run semantic lookups, and present them with extra context from your vector store.

Yes, your credentials are encrypted and stored in an ephemeral, zero-trust sandbox. The MCP Server only reads your highlights and books when executing tool calls. Your private reading data is never cached or leaked.

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