How to Use the Linkwarden MCP in Google ADK

Q: How do I configure Google ADK to authenticate with Linkwarden?

You define a McpToolset using the Vinkius HTTP transport URL. Vinkius manages the secure storage of your Linkwarden credentials, meaning your Google ADK agent only needs one endpoint token to start calling tools.

Q: Can I limit my Google ADK agent to read-only Linkwarden operations?

Yes, you can use the toolnames filter in your StreamableHttpServerParameters setup. By specifying only tools like getlink and listcollections, you prevent the agent from executing destructive actions.

Q: How does Google ADK handle large file uploads to Linkwarden?

The SDK uses streamable HTTP transports to execute uploadarchiveforlink without hitting memory limits. This allows your Gemini agent to upload heavy web archives and PDFs directly to your Linkwarden instance.

Q: Can my agent pull RSS feeds using this setup?

Yes, your agent can call listrss to fetch your feed subscriptions. This allows you to build automated digest agents that read your feeds and bookmark important updates.

Connect Gemini models to Linkwarden using Google ADK to archive, search, and structure web pages at enterprise scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linkwarden MCP to Google ADK

Create your Vinkius account to connect Linkwarden to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Linkwarden with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context ingestion with Google ADK

Executing `get_link` allows your Gemini agent to pull raw web content directly into its million-token context window. This integration uses this MCP Server to feed your enterprise knowledge base with archived pages stored in your private collection. The agent uses `list_collections` to map your entire bookmark hierarchy before running deep semantic searches across your saved materials. This makes your archived knowledge instantly accessible to your cloud pipelines.

Automated archival pipelines via Google ADK

Calling `upload_standalone_archive` from a Google ADK pipeline lets you ingest web data directly from BigQuery sources. Your agent processes raw text, generates a clean HTML snapshot, and saves it to your default collection in one step. To keep content fresh, the agent triggers `archive_link` whenever a monitored source changes. This keeps your offline mirrors in sync with live web targets without manual script maintenance.

Metadata extraction and collection management

Your agent calls `create_collection` to dynamically build target structures based on your Google Cloud data classification. The Google ADK coordinates these calls to align your bookmarking hierarchy with your enterprise taxonomy. The agent then runs `bulk_update_links` to apply tags and move assets into these new collections. This ensures that every saved resource is properly indexed for your downstream machine learning models.

Setup guide

Set up Linkwarden 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 Linkwarden 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="Linkwarden_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Linkwarden 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 Linkwarden. 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 Linkwarden 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 Linkwarden MCP in Google ADK

You define a `McpToolset` using the Vinkius HTTP transport URL. Vinkius manages the secure storage of your Linkwarden credentials, meaning your Google ADK agent only needs one endpoint token to start calling tools.

Yes, you can use the `tool_names` filter in your `StreamableHttpServerParameters` setup. By specifying only tools like `get_link` and `list_collections`, you prevent the agent from executing destructive actions.

The SDK uses streamable HTTP transports to execute `upload_archive_for_link` without hitting memory limits. This allows your Gemini agent to upload heavy web archives and PDFs directly to your Linkwarden instance.

Yes, your agent can call `list_rss` to fetch your feed subscriptions. This allows you to build automated digest agents that read your feeds and bookmark important updates.

Vinkius executes this MCP Server inside a secure, zero-trust V8 isolate. Your bookmark metadata and API keys are processed ephemerally, ensuring your private web archives remain completely isolated from external networks.

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