How to Use the Linkwarden MCP in LlamaIndex

Q: How does LlamaIndex handle Linkwarden PDF archives?

LlamaIndex uses getarchive to retrieve the PDF or screenshot binary from Linkwarden. It then parses the file and inserts the text chunks directly into your vector index.

Q: Can I filter which collections get indexed?

Yes. You can use the listcollections tool to let your agent filter collections by name before pulling link details.

Index your Linkwarden bookmarks directly into LlamaIndex. Build RAG pipelines that query your actual archived web pages.

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 LlamaIndex

Create your Vinkius account to connect Linkwarden to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

RAG pipelines powered by Linkwarden archives

LlamaIndex turns your web archives into structured knowledge bases by calling `get_archive` and `stream_preserved_view`. The framework pulls raw HTML or PDF snapshots directly into your vector store. Your queries are answered using your actual saved pages, not old training data. This eliminates hallucination. The LlamaIndex agent checks your Linkwarden collections, retrieves the exact preserved page, and indexes it. Your search results stay grounded in the actual text you archived.

Semantic search across Linkwarden collections

Instead of searching bookmarks by static tags, use LlamaIndex to query them semantically. The framework calls `list_collections` and `get_public_collection_links` to gather your bookmarks. It then builds a local index that understands the actual meaning behind your saved items. When you search, the LlamaIndex agent matches your intent to the correct bookmark. It can even suggest updates to your organization by calling `update_link` to apply better tags based on semantic clustering.

Automated knowledge curation with MCP Server tools

Keep your knowledge base fresh without manual work. This MCP Server lets LlamaIndex run background jobs that call `get_dashboard_v2` to scan your recent links. It analyzes the content and uses `create_highlight` to mark key passages that match your research topics. If the system finds gaps in your index, it can use `upload_standalone_archive` to pull in missing reference documents. This turns your Linkwarden instance into a self-feeding data source for your local AI models.

Setup guide

Set up Linkwarden 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 Linkwarden 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 Linkwarden tools.",
)
response = await agent.run("List recent Linkwarden 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 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 LlamaIndex

Use llama-index-tools-mcp to initialize the client. Convert the Linkwarden tools using McpToolSpec and pass them to your query engine or agent.

Yes. By providing your Linkwarden API key to the MCP Server, LlamaIndex can access private collections using `get_collection` and index their contents securely.

LlamaIndex uses `get_archive` to retrieve the PDF or screenshot binary from Linkwarden. It then parses the file and inserts the text chunks directly into your vector index.

Yes. You can use the `list_collections` tool to let your agent filter collections by name before pulling link details.

Your collection metadata and archived files are processed in a zero-trust, ephemeral environment. Vinkius ensures that no Linkwarden data or access tokens are permanently stored or exposed to third parties during indexing.

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