How to Use the Crafter CMS MCP in LlamaIndex

Q: Can I build a RAG pipeline using Crafter CMS and LlamaIndex?

Yes, you can index live content retrieved via searchcrafterdelivery directly into your vector store. This lets your LlamaIndex agent answer queries using fresh production data.

Q: How does LlamaIndex prevent hallucinated paths in Crafter CMS?

The agent indexes your actual Git hierarchy using getstudiotree. It checks this local index to verify paths before executing any content modifications.

Q: Can LlamaIndex query site configurations through this MCP Server?

Yes, the getsiteconfig tool pulls your active GraphQL URL limits directly into the agent's context. LlamaIndex indexes these limits to optimize its query strategies.

Q: How do I filter the tools available to my LlamaIndex agent?

You use the allowedtools filter in the LlamaIndex MCP tool spec. This lets you restrict write operations like wipestudioxml while keeping read operations open.

Index live Crafter CMS content structures directly into LlamaIndex vector stores using 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 Crafter CMS MCP to LlamaIndex

Create your Vinkius account to connect Crafter CMS 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 Crafter CMS with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Crafter CMS schemas for LlamaIndex RAG

The `get_site_globals` tool retrieves the structured rules and active configurations of your Crafter CMS setup so your LlamaIndex agent can index them. By turning these rules into searchable vector embeddings, your agent understands your site's architecture before writing queries. This prevents your RAG applications from hallucinating API endpoints or field structures. Your agent queries the local vector store first to pull the correct schema before executing any live tools.

Search delivery engines using this MCP Server

The `search_crafter_delivery` tool inspects deep internal arrays within your delivery engine to pull live content directly into LlamaIndex. Your agent parses these search results and indexes them, making live production data immediately available for semantic queries. Instead of relying on static documents, your RAG pipeline uses fresh content from the delivery engine. This ensures your user-facing search answers are always grounded in real-time site data.

Safe XML tree exploration in LlamaIndex

The `get_studio_tree` tool extracts the nested XML structures and Git hierarchies of your Crafter CMS repository for indexing. LlamaIndex stores this structural data to help your agent map out content relationships across your entire workspace. When you ask your agent to modify a page, it references this indexed map to find the exact file path. This keeps your Git repository structured correctly and prevents orphaned XML files.

Setup guide

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

Yes, you can index live content retrieved via `search_crafter_delivery` directly into your vector store. This lets your LlamaIndex agent answer queries using fresh production data.

The agent indexes your actual Git hierarchy using `get_studio_tree`. It checks this local index to verify paths before executing any content modifications.

Yes, the `get_site_config` tool pulls your active GraphQL URL limits directly into the agent's context. LlamaIndex indexes these limits to optimize its query strategies.

You use the `allowed_tools` filter in the LlamaIndex MCP tool spec. This lets you restrict write operations like `wipe_studio_xml` while keeping read operations open.

Yes, all site configurations and GraphQL queries are processed within a zero-trust V8 isolate. Your endpoint tokens and API keys never leave the secure runtime environment.

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