How to Use the Metatext MCP in LlamaIndex

Q: How do I index Metatext dataset records in LlamaIndex?

You use the listdatasetrecords tool to pull text samples from your dataset. LlamaIndex then parses these records into Document nodes and builds a vector index for semantic search.

Q: Can LlamaIndex query Metatext model metadata?

Yes. Your agent can call getmodeldetails to inspect model schemas and labels, allowing it to format retrieval queries that match the exact expected input structure.

Index Metatext datasets and model metadata directly into your LlamaIndex knowledge graphs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metatext MCP to LlamaIndex

Create your Vinkius account to connect Metatext 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 Metatext with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Metatext datasets into searchable vectors

The `list_nlp_datasets` and `list_dataset_records` tools allow your LlamaIndex pipeline to pull text records directly from your training data. Instead of exporting CSV files, your agent queries these datasets and indexes the records into a local vector store. This lets you run semantic search over your raw training data to find similar examples. When building RAG applications, this setup ensures your agent has access to real, grounded examples from your actual datasets. It bridges the gap between your training data store and your live retrieval systems.

Query active model deployments dynamically

The `list_model_deployments` tool retrieves the list of all active models currently running on your account. Your LlamaIndex agent uses this list to understand which models are online and ready to accept prediction inputs. It can then fetch specific parameters using `get_model_details` to configure its queries. This eliminates the risk of sending RAG payloads to offline or deprecated models. Your agent verifies the deployment status before executing any inference steps.

Run grounded predictions using MCP Server tools

The `run_model_inference` tool executes predictions on your custom models using context retrieved from your LlamaIndex vector index. Your agent pulls relevant documents, formats them into a prompt, and sends the text to your specialized classifier. This combines the retrieval power of LlamaIndex with the specific extraction capabilities of your Metatext models. You get the output back as structured data that can be re-indexed or used to update your index configurations. It makes your custom models an active part of your retrieval loop.

Setup guide

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

You use the `list_dataset_records` tool to pull text samples from your dataset. LlamaIndex then parses these records into Document nodes and builds a vector index for semantic search.

Yes. Your agent can call `get_model_details` to inspect model schemas and labels, allowing it to format retrieval queries that match the exact expected input structure.

No. Vinkius manages the authentication details securely. You configure the MCP connection once, and your LlamaIndex client accesses all 10 tools using a single secure endpoint token.

Yes. The MCP tool can be called directly by your query engine or agent to classify or extract data from retrieved text nodes.

Yes. All text strings sent for inference or dataset creation are handled in zero-trust, ephemeral environments. Your raw data is transmitted directly to the Metatext API over HTTPS and is never cached or stored on Vinkius servers.

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