How to Use the Readwise MCP in Google ADK

Q: How do I initialize the Readwise MCP Server in Google ADK?

Use the McpToolset class with your Vinkius HTTP endpoint URL. Pass this toolset into your LlmAgent to let Gemini auto-discover the Readwise tools.

Q: Can Gemini search my Readwise library using Google ADK?

Yes, Gemini uses searchbooks and searchhighlights to locate specific passages. It processes the raw text return directly within its long-context window.

Q: Can I write new highlights from Google ADK?

Yes, the agent calls createhighlight to save new notes generated during your cloud workflows. It can also use updatehighlight to modify existing records.

Feed millions of tokens of book notes and highlights directly into your Google ADK pipelines from Readwise.

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 Google ADK

Create your Vinkius account to connect Readwise to Google ADK — 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Map Readwise books to Google ADK context windows

`list_books` and `get_book` feed your Google ADK agent with raw metadata to map out your entire Readwise reading library. Because Gemini handles massive context windows, your Google ADK agent can ingest entire Readwise book structures before deciding which highlights to analyze. The Google ADK agent coordinates these tools to pull complete lists of Readwise titles. It then cross-references this Readwise catalog with your enterprise data in BigQuery via the MCP Server to find gaps in your team's research.

Bulk export highlights for Google ADK analysis

`export_highlights` pulls your entire history of Readwise reading notes into Google ADK for long-context synthesis. This Readwise tool supports incremental updates, allowing your Google ADK pipeline to fetch only the newest entries and append them to your Vertex AI datasets. By running this tool inside your Google Cloud environment, you can batch process thousands of Readwise highlights via Google ADK. The Google ADK agent organizes the incoming Readwise text stream and updates your centralized BigQuery storage without manual intervention.

Query the Readwise MCP Server via Google ADK tools

`search_highlights` and `list_highlights` expose your curated Readwise knowledge directly to Gemini's reasoning engine in Google ADK. Your Google ADK agent calls these Readwise MCP tools to retrieve specific quotes, notes, and tags matching a user's prompt. You can restrict which Readwise tools are exposed by passing a filtered list to the Google ADK `McpToolset`. This ensures your Gemini agent in Google ADK only accesses search capabilities and cannot execute destructive Readwise tools like `delete_highlight`.

Setup guide

Set up Readwise MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Readwise tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Readwise_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Readwise tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use the `McpToolset` class with your Vinkius HTTP endpoint URL. Pass this toolset into your `LlmAgent` to let Gemini auto-discover the Readwise tools.

Yes, Gemini uses `search_books` and `search_highlights` to locate specific passages. It processes the raw text return directly within its long-context window.

The framework relies on the server's built-in handling, but you can also configure your Google ADK pipeline to throttle calls to `export_highlights` when running large batch jobs.

Yes, the agent calls `create_highlight` to save new notes generated during your cloud workflows. It can also use `update_highlight` to modify existing records.

Yes, the MCP connection runs through an ephemeral sandbox that handles your API token securely. No book metadata, highlights, or tags are logged or cached on the Vinkius platform.

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