How to Use the Outlier Detection Engine MCP in LangChain

Run deterministic math inside your LangChain pipelines to flag anomalies before they pollute your downstream vectors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Outlier Detection Engine MCP to LangChain

Create your Vinkius account to connect Outlier Detection Engine to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Outlier Detection Engine with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Stop LLM guessing in LangChain pipelines

The `detect_outliers` tool stops your LangChain agents from guessing which rows are statistical anomalies. This MCP server plugs directly into your chains so your agent runs the math, gets the exact indexes of the bad rows, and routes them to a clean-up chain before they hit your database.

Trace anomaly detection via LangSmith

By integrating the `detect_outliers` tool with LangSmith, you can trace the exact inputs and outputs of every statistical run. You see exactly when the calculation executed, what the threshold was, and how long it took.

Multi-step data cleaning chains

With the `detect_outliers` tool, you build multi-step chains where the output of your statistical check feeds the next step. Your agent handles the decision logic while the underlying server executes the heavy math locally on your raw CSV or JSON files.

Setup guide

Set up Outlier Detection Engine 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 Outlier Detection Engine 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({
    "outlier-detection-engine-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 Outlier Detection Engine 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 simple-statistics. 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 Outlier Detection Engine 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 Outlier Detection Engine MCP in LangChain

You install the MCP adapters and pass the tools directly to your agent constructor. The agent calls `detect_outliers` when it needs to inspect a dataset, receiving clean JSON arrays of flagged rows.

Yes, every tool invocation is fully tracked. You can see the exact parameters passed to `detect_outliers` and the resulting indices in your LangSmith dashboard.

Use the multi-server adapter to merge this statistical server with your other endpoints. Your agent can then query a database, pass the resulting rows to `detect_outliers`, and write the clean data back.

Yes, you can specify the exact threshold when calling the tool. Your agent can dynamically adjust this value based on the variance it observes in previous steps of the chain.

Absolutely. The statistical calculations run entirely inside a local V8 sandbox on your machine. No raw tabular data or file contents are ever sent to external APIs or third-party 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