How to Use the GroundX MCP in LlamaIndex

Q: How does LlamaIndex convert GroundX tool outputs into searchable nodes?

The LlamaIndex McpToolSpec takes the text returned by searchcontent or searchdocuments and wraps it in a standard Document object. From there, your indexer processes it like any other data source.

Q: Can I use GroundX to ingest websites directly from LlamaIndex?

Yes, your LlamaIndex agent can call ingestwebsite with a target URL to start the crawl. It then polls getingeststatus to verify completion before indexing the new content.

Q: How do I register GroundX tools with a LlamaIndex FunctionAgent using the MCP tool spec?

Install llama-index-tools-mcp and pass the Vinkius HTTP URL to the client. Call totoollistasync on the tool spec and pass the resulting list to your LlamaIndex agent.

Q: What is the difference between searchcontent and searchdocuments in LlamaIndex?

Use searchcontent when your LlamaIndex agent needs a broad semantic search across all buckets. Use searchdocuments when you need to target specific files using metadata filters.

Index GroundX search results directly into your LlamaIndex vector stores with 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 GroundX MCP to LlamaIndex

Create your Vinkius account to connect GroundX 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 GroundX with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed GroundX search data into LlamaIndex

The `search_content` tool allows your LlamaIndex agent to query your GroundX buckets and convert the raw text chunks into searchable document nodes. You don't have to build custom chunking parsers because the MCP Server delivers pre-optimized text. Your LlamaIndex application then indexes these nodes into its local vector store for fast, hybrid retrieval. This setup ensures your local index always has access to the semantic search capabilities of the platform.

Manage GroundX buckets from LlamaIndex agents

The `create_bucket` tool gives your LlamaIndex agent direct control over data organization from within its query pipeline. When a user uploads a new dataset, the agent creates a bucket and runs `ingest_documents` to upload the files. To keep track of these containers, the agent uses `list_buckets` and `list_content` to verify what data is available before running a query. This prevents your LlamaIndex indices from getting cluttered with duplicate documents.

Build dynamic RAG pipelines with this MCP Server

The `list_workflows` tool lets your LlamaIndex agent discover and execute pre-configured RAG workflows managed by GroundX. This means you can offload complex search pipelines to the server instead of writing them in Python. You get the flexibility of LlamaIndex's indexing paired with this MCP Server's search speed. If a workflow isn't active, the agent uses `search_documents` to run metadata-filtered searches directly.

Setup guide

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

The LlamaIndex `McpToolSpec` takes the text returned by `search_content` or `search_documents` and wraps it in a standard Document object. From there, your indexer processes it like any other data source.

Yes, your LlamaIndex agent can call `ingest_website` with a target URL to start the crawl. It then polls `get_ingest_status` to verify completion before indexing the new content.

Install `llama-index-tools-mcp` and pass the Vinkius HTTP URL to the client. Call `to_tool_list_async` on the tool spec and pass the resulting list to your LlamaIndex agent.

Use `search_content` when your LlamaIndex agent needs a broad semantic search across all buckets. Use `search_documents` when you need to target specific files using metadata filters.

All crawled websites and uploaded documents are stored in secure, isolated buckets on the platform. The Vinkius MCP gateway uses ephemeral execution to ensure your search queries and document contents are never cached or exposed to 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