How to Use the Nyckel ML MCP in LlamaIndex

Q: Can LlamaIndex query Nyckel ML samples for context injection?

Yes, it can. Your agent uses listmlsamples to pull existing training data and inject it directly into the prompt context for better responses.

Index your Nyckel ML classifications and training samples directly into 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 Nyckel ML MCP to LlamaIndex

Create your Vinkius account to connect Nyckel ML 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 Nyckel ML with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground RAG pipelines with live classification data

`get_ml_function` retrieves your active model schemas and transfers them directly into your LlamaIndex knowledge base using this MCP Server. This keeps your agent grounded in your actual classification taxonomy rather than hallucinating labels. By feeding this structural data into your index, your query engines understand exactly what your models do. Your agent reads the function metadata to choose the right classification path.

Index search results using LlamaIndex

`semantic_search` queries your Nyckel index and returns the closest matching labeled samples. LlamaIndex takes these search outputs and converts them into document nodes for immediate vector indexing. This means your search results become part of a queryable memory. Your RAG application references past classifications to answer user queries with higher precision.

Automate dataset audits from your index

`list_ml_samples` pulls your entire training set into LlamaIndex for evaluation. Your agent analyzes these samples against your current production data to find labeling drift or gaps in your training coverage. Once it spots an issue, the agent uses `annotate_ml_sample` to correct the label. This keeps your training data clean and your model accuracy high without exporting CSV files.

Setup guide

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

Install the LlamaIndex MCP tool package first. Then, initialize the client using the Vinkius URL and pass the tools to your FunctionAgent.

Yes, it can. Your agent uses `list_ml_samples` to pull existing training data and inject it directly into the prompt context for better responses.

The agent calls the search tool, and LlamaIndex packages the returned matches as nodes that your query engine can synthesize into a final answer.

Yes, you can. Use the allowed tools filter during initialization to restrict your agent to specific tools like classification while blocking deletion tools.

All your uploaded samples and labels are stored securely in your Nyckel account. The Vinkius MCP Server sandbox handles the API traffic using ephemeral environments that delete data post-execution.

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