How to Use the Hive AI MCP in LlamaIndex

Q: Can I filter which Hive AI tools my LlamaIndex agent can access?

Yes, you can use the allowedtools filter when setting up the MCP tool spec. This lets you restrict your LlamaIndex agent to specific tools like moderatetext while hiding administrative tools.

Q: How do I check if my project configuration is correct?

Call getprojectdetails to retrieve your active configuration. The LlamaIndex agent can use this data to verify that your active models match your indexing rules.

Index Hive AI moderation verdicts directly into your LlamaIndex vector store 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 Hive AI MCP to LlamaIndex

Create your Vinkius account to connect Hive AI 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 Hive AI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your LlamaIndex RAG pipeline with Hive AI

This MCP Server lets your LlamaIndex agent index real-time moderation verdicts directly into your vector database. When the LlamaIndex agent calls `moderate_text` or `moderate_image`, the returned safety scores are stored alongside your documents. This prevents your LlamaIndex retrieval systems from pulling flagged or unsafe content during query time. By indexing these Hive AI safety evaluations, your LlamaIndex search application gains a memory of past violations. The LlamaIndex agent can query past sessions to see if a specific user has a history of triggering moderation blocks, making safety decisions context-aware.

Scan and catalog synthetic content in your index

Keep your LlamaIndex knowledge base clean by scanning incoming documents for AI-generated text and images before indexing them. Your LlamaIndex agent runs `detect_ai_generated_text` and `detect_ai_generated_image` on incoming data streams. Only verified human-generated content gets written to your LlamaIndex index. If synthetic content is allowed, the LlamaIndex agent tags the metadata with the detection probability score. This lets you filter LlamaIndex search results based on whether the source material was written by a human or an AI model.

Process large media indexes asynchronously

Indexing video and audio databases in LlamaIndex requires handling long-running background tasks. Your LlamaIndex agent can dispatch heavy files using `moderate_video_async` and `moderate_audio_async` without blocking your indexing pipeline. The LlamaIndex agent stores the task metadata and continues processing other files. You can write a LlamaIndex query engine that checks `get_async_task_status` and retrieves completed analyses via `get_async_task_result`. Once the Hive AI results are ready, the engine updates the document metadata in your vector store.

Setup guide

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

Install llama-index-tools-mcp and initialize the MCP client with your server URL. Wrap it in McpToolSpec and pass the tool list to your LlamaIndex FunctionAgent.

Yes, you can use the allowed_tools filter when setting up the MCP tool spec. This lets you restrict your LlamaIndex agent to specific tools like `moderate_text` while hiding administrative tools.

The LlamaIndex agent converts the JSON response from tools like `get_async_task_result` into document nodes. These nodes are then indexed into your vector store with custom metadata tags.

Call `get_project_details` to retrieve your active configuration. The LlamaIndex agent can use this data to verify that your active models match your indexing rules.

All text and audio payloads are routed directly through an encrypted TLS tunnel from the V8 isolate sandbox to Hive's API. The sandbox is completely stateless, meaning no data persists on Vinkius infrastructure after the tool execution finishes.

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