How to Use the Duda MCP in LlamaIndex

Q: How do I index my Duda sites into a LlamaIndex vector store?

Run listdudasites to get the site list, then fetch details using getsitedetails. The tool output is converted into document nodes, which LlamaIndex indexes for semantic search.

Q: Can I search Duda templates using LlamaIndex semantic queries?

Yes. Your agent calls listsitetemplates to gather available layouts, then indexes the metadata. You can then query the index to find templates that match specific client design requests.

Q: How does LlamaIndex prevent hallucinations when checking Duda sites?

The agent queries actual API data using quicksitehealthaudit and indexes the results. This limits the context window to real-time facts, ensuring answers are grounded in actual site status.

Q: What is the fastest way to look up a site by its domain?

Use searchsitesbydomain to locate the site ID instantly. Once the agent has the ID, it can pull full configuration details without scanning your entire account.

Index live Duda site configurations and client profiles directly into LlamaIndex via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duda MCP to LlamaIndex

Create your Vinkius account to connect Duda 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 Duda with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vector search over active Duda site settings

Turn your live site data into a searchable knowledge base. Your LlamaIndex agent runs `list_duda_sites` to gather all active instances, then retrieves granular configurations via `get_site_details` for indexing. This MCP Server integration allows you to run semantic queries over your actual site setups. Instead of guessing which site has a specific feature active, you query the index and get immediate answers.

Semantic queries on client account profiles

Stop digging through client databases to check permissions. Your agent calls `list_client_accounts` and `get_client_account_profile` to pull real-time organizational data, then indexes the text output. You can ask your agent which clients have specific access levels. The query engine matches your natural language question against the indexed profile data for factual, hallucination-free answers.

Indexing dynamic site collections for RAG

Pull live structured content into your retrieval-augmented generation pipelines. By calling `list_site_collections`, your agent indexes the schemas and content of your dynamic pages. This MCP setup ensures your agent answers questions based on actual database structures rather than outdated documentation. You get a direct pipeline from your site databases to your LlamaIndex vector store.

Setup guide

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

Run `list_duda_sites` to get the site list, then fetch details using `get_site_details`. The tool output is converted into document nodes, which LlamaIndex indexes for semantic search.

Yes. Your agent calls `list_site_templates` to gather available layouts, then indexes the metadata. You can then query the index to find templates that match specific client design requests.

The agent queries actual API data using `quick_site_health_audit` and indexes the results. This limits the context window to real-time facts, ensuring answers are grounded in actual site status.

Use `search_sites_by_domain` to locate the site ID instantly. Once the agent has the ID, it can pull full configuration details without scanning your entire account.

All site settings and template details are processed in memory within a zero-trust V8 sandbox. No data is cached or stored long-term, keeping your site configurations secure from external exposure.

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