How to Use the Kontent.ai MCP in LlamaIndex

Q: How do I register the Kontent.ai MCP Server tools in LlamaIndex?

Install llama-index-tools-mcp and instantiate BasicMCPClient with your Vinkius server URL. Use McpToolSpec to load the tools and pass them to your FunctionAgent as an asynchronous tool list.

Q: Can LlamaIndex search across taxonomies?

Yes, the agent can call listtaxonomies or gettaxonomygroup to fetch your classification system. It can then use these categories as metadata filters to narrow down semantic search queries.

Q: Does this MCP Server support indexing multiple languages in LlamaIndex?

Yes, the agent runs listprojectlanguages to discover all configured languages. It then fetches the corresponding localized content items to build separate, language-specific search indexes.

Q: How do I limit which tools LlamaIndex can access?

You can use the allowedtools filter when initializing your tool specification. This restricts the agent to specific operations, like only allowing searchkontentai while hiding schema-level tools.

Q: What happens to my Kontent.ai content during indexing?

Only the text and metadata fetched via getcontentitem are processed in memory to generate embeddings. Vinkius runs the MCP Server in an ephemeral sandbox, meaning no headless CMS data is cached or stored permanently outside your designated vector database.

Build RAG pipelines that index live Kontent.ai headless content directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontent.ai MCP to LlamaIndex

Create your Vinkius account to connect Kontent.ai 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 Kontent.ai with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounded RAG with live CMS data

Stop relying on outdated static exports for your retrieval-augmented generation. LlamaIndex uses `list_content_items` to pull the latest production drafts and indexes them on the fly, eliminating LLM hallucinations. The agent queries `get_content_item` to fetch full body text and metadata. This guarantees your RAG application always answers users using the exact text active in your headless CMS.

Semantic search over assets

Searching through massive media libraries is normally a painful manual process. This MCP Server exposes `list_content_assets`, allowing LlamaIndex to fetch metadata for images, documents, and videos to build a searchable asset index. Your agent can then parse descriptions, alt text, and file details. It connects these assets directly to relevant text nodes in your vector store for richer search results.

Schema-aware indexing in LlamaIndex

To index content correctly, your pipeline needs to understand how it is structured. LlamaIndex queries `list_content_types` and `get_content_type_element` to map out fields before running ingest jobs. This prevents formatting errors when converting rich text or multi-choice elements into vector nodes. Your index retains the exact logical relationships defined in your Kontent.ai schema.

Setup guide

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

Install `llama-index-tools-mcp` and instantiate `BasicMCPClient` with your Vinkius server URL. Use `McpToolSpec` to load the tools and pass them to your `FunctionAgent` as an asynchronous tool list.

Yes, the agent can call `list_taxonomies` or `get_taxonomy_group` to fetch your classification system. It can then use these categories as metadata filters to narrow down semantic search queries.

Yes, the agent runs `list_project_languages` to discover all configured languages. It then fetches the corresponding localized content items to build separate, language-specific search indexes.

You can use the `allowed_tools` filter when initializing your tool specification. This restricts the agent to specific operations, like only allowing `search_kontent_ai` while hiding schema-level tools.

Only the text and metadata fetched via `get_content_item` are processed in memory to generate embeddings. Vinkius runs the MCP Server in an ephemeral sandbox, meaning no headless CMS data is cached or stored permanently outside your designated vector database.

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