How to Use the Hive AI MCP in LangChain

Q: Can I trace Hive AI API latency inside LangChain?

Yes, every tool call like moderatetext is fully tracked if you have LangSmith enabled. You will see exactly how long the API took to respond and what payload was sent inside your LangChain run.

Q: Does LangChain support asynchronous Hive AI tasks?

Yes, you can run moderatevideoasync in one step of your LangChain graph and poll for results in a later node. The MCP adapter handles the async execution model natively.

Q: How do I select which moderation model to use?

You can query your active configuration by calling listavailablemodels. This tool returns the exact model IDs available in your project so your LangChain agent always uses the correct version.

Run multi-step moderation chains with this MCP Server directly inside your LangChain pipelines.

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 LangChain

Create your Vinkius account to connect Hive AI to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated moderation chains in LangChain

This MCP Server lets LangChain agents chain raw content ingestion directly into Hive AI verification steps. When a user posts content, your LangChain pipeline grabs the payload, runs `moderate_text` to catch violations, and routes the output to the next node. If the text passes, the LangChain agent triggers `moderate_image` on associated assets without needing manual routing logic. You get full observability through LangSmith tracing to watch how these Hive AI tools execute. Every time the LangChain agent calls `get_project_details` to verify model configurations, you see the exact payload, latency, and token count. It makes debugging complex multi-step LangChain pipelines straightforward.

Detect synthetic media inside autonomous pipelines

Stop generative spam before it hits your database by inserting Hive AI detection tools into your active LangGraph runs. Your LangChain agent evaluates uploads by calling `detect_ai_generated_image` and `detect_ai_generated_text` in parallel. This setup stops bot-created content from polluting your LangChain application without slowing down legitimate human posters. The LangChain agent processes these evaluations as standard links in your graph. If a file flags as synthetic, the LangGraph routes the message to a quarantine state automatically. You don't have to write custom glue code to handle the branching logic in your LangChain workflows.

Handle heavy video and audio files asynchronously

Processing large media files shouldn't block your main LangChain execution thread. Your LangChain agent can initiate background tasks using `moderate_video_async` and `moderate_audio_async`, allowing the chain to continue handling other user actions. The LangChain pipeline stores the task ID and moves to the next node. A separate polling LangChain adapter can periodically call `get_async_task_status` and `get_async_task_result` to fetch the final moderation verdict. This decouples heavy Hive AI media processing from real-time LangChain user interactions, keeping your application responsive.

Setup guide

Set up Hive AI MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Hive AI tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hive-ai-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Hive AI transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use the langchain-mcp-adapters library to convert the MCP server tools. Once connected, call client.get_tools() and pass them directly to your LangChain agent constructor.

Yes, every tool call like `moderate_text` is fully tracked if you have LangSmith enabled. You will see exactly how long the API took to respond and what payload was sent inside your LangChain run.

Yes, you can run `moderate_video_async` in one step of your LangChain graph and poll for results in a later node. The MCP adapter handles the async execution model natively.

You can query your active configuration by calling `list_available_models`. This tool returns the exact model IDs available in your project so your LangChain agent always uses the correct version.

Your text, images, and video files are sent directly to Hive AI endpoints via Vinkius's secure, ephemeral V8 sandbox. No data is stored on Vinkius servers, and the sandbox destroys itself after the tool call completes.

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