How to Use the MonkeyLearn MCP in LlamaIndex

Q: How do I configure LlamaIndex to use the MonkeyLearn MCP Server?

Install the required package with pip install llama-index-tools-mcp. Then, instantiate the BasicMCPClient, convert it using McpToolSpec, and pass the tools to your FunctionAgent.

Q: Can LlamaIndex use MonkeyLearn to filter vector search results?

Yes, it can. You run classifytext on incoming queries to detect sentiment or topic, then use those tags as metadata filters in your vector database query.

Q: How does LlamaIndex handle changes in my MonkeyLearn classifier tags?

Your agent calls listclassifiertags to fetch the latest tag structure. It then updates its indexing rules to match the new taxonomy automatically.

Q: Can I run complex text extraction pipelines during document ingestion?

Yes. You use runworkflow to process documents during the ingestion phase. This extracts entities and classifies topics in a single step before the text hits your vector store.

Index your LlamaIndex RAG pipelines with real-time text classifications from MonkeyLearn.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MonkeyLearn MCP to LlamaIndex

Create your Vinkius account to connect MonkeyLearn 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 MonkeyLearn with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index MonkeyLearn classifications into LlamaIndex

Your LlamaIndex RAG application uses `classify_text` to tag raw documents before indexing them. This metadata tagging cuts down your search space by 40%. The agent queries these tagged nodes using semantic search. Here's the thing about filtering. By filtering searches based on the sentiment tags returned by `list_classifier_tags`, you prevent irrelevant documents from polluting your context. It's that simple.

Ground your vector queries using this MCP Server

This MCP Server lets your indexer call `extract_text_entities` to pull structured metadata from unstructured text. You can automatically populate your index metadata with extracted names, locations, or product IDs. This adds structure to raw text. This extraction makes your search queries more accurate. Instead of relying on raw text matches, LlamaIndex filters documents using the exact entities found by `get_extractor_details`.

Search past classification runs and model structures

The `list_classifiers` tool lets LlamaIndex query your active machine learning models to map out your classification taxonomy. The agent stores this taxonomy in its index to understand how your support data is organized. This builds a smarter knowledge base. By calling `list_extractor_tags`, the agent dynamically updates its index schema whenever you add new tags. This keeps your search filters in sync with your active text classifiers.

Setup guide

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

Install the required package with `pip install llama-index-tools-mcp`. Then, instantiate the BasicMCPClient, convert it using McpToolSpec, and pass the tools to your FunctionAgent.

Yes, it can. You run `classify_text` on incoming queries to detect sentiment or topic, then use those tags as metadata filters in your vector database query.

Your agent calls `list_classifier_tags` to fetch the latest tag structure. It then updates its indexing rules to match the new taxonomy automatically.

Yes. You use `run_workflow` to process documents during the ingestion phase. This extracts entities and classifies topics in a single step before the text hits your vector store.

Yes, Vinkius uses a zero-trust model where your document text only passes through secure, isolated memory spaces. No raw text or classification outputs are cached or saved on the Vinkius hosting platform.

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