How to Use the Readwise MCP in LangChain

Q: Can I run multi-server setups with Readwise and LangChain?

Absolutely. The MultiServerMCPClient aggregates tools from different sources into one list. Your agent can query your Readwise books and search other databases using the same MCP connection.

Q: How does the incremental export handle rate limits?

The exporthighlights tool supports an updated-after filter to pull only new data. This keeps payloads small and prevents your agent from hitting Readwise API rate limits during routine syncs.

Feed your Readwise reading history directly into LangChain chains to build custom research agents.

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 LangChain

Create your Vinkius account to connect Readwise to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chaining highlights into your LangChain pipelines

Let your agent pull specific reading notes and pipe them directly into downstream steps. The `list_highlights` tool fetches text, locations, and tags, while `get_book` grabs the surrounding context. Your pipeline handles these outputs as raw variables, passing them to the next prompt without manual copy-pasting. You can trace the entire execution flow using LangSmith. This lets you monitor latency and token counts every time your agent triggers `search_highlights` or updates a tag. It makes debugging multi-step reasoning pipelines straightforward.

Automated review queues with LangChain agents

Build a background worker that checks your daily reading list. The agent uses `get_daily_review` to pull your active cards and processes them according to your custom prompt templates. It can automatically categorize items or flag outdated cards. If a highlight needs an update, the agent triggers `update_highlight` directly. You don't have to write custom wrappers for the Readwise API. This MCP Server exposes these tools natively so your chain can edit data on the fly.

Filtering library sources in active chains

Your LangChain agent can filter books by where they came from before running a synthesis step. By invoking `list_books_by_source` or `list_books_by_category`, the model isolates Kindle highlights from articles or PDFs. This keeps your context window clean. Stop dumping your entire library into one giant prompt. It is expensive and slow. Instead, let the agent run a targeted query using `search_books` to pull exactly what the task requires.

Setup guide

Set up Readwise MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Readwise tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "readwise-alternative-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Readwise transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapter package and initialize the client with your endpoint. Use `MultiServerMCPClient` to fetch the tools, then pass them to your agent constructor. The agent uses the MCP standard to grab tools like `list_highlights` on the fly.

Yes, if you use LangSmith tracing. Every time your agent calls `list_books` or `export_highlights`, LangSmith logs the exact execution time and token usage. This helps you find bottlenecks in your research chains.

Absolutely. The `MultiServerMCPClient` aggregates tools from different sources into one list. Your agent can query your Readwise books and search other databases using the same MCP connection.

The `export_highlights` tool supports an updated-after filter to pull only new data. This keeps payloads small and prevents your agent from hitting Readwise API rate limits during routine syncs.

Your tokens and highlights stay isolated within Vinkius's secure sandbox. The MCP Server only communicates with the Readwise API to fetch your books and tags. No external databases store your reading history.

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