How to Use the Ninox MCP in LangChain

Q: How do I initialize the Ninox MCP Server inside my LangChain agent?

Install langchain-mcp-adapters and langgraph via pip. Initialize the MultiServerMCPClient with the Vinkius endpoint URL, call gettools(), and pass those tools directly to your agent constructor.

Q: Can my LangChain agent query multiple Ninox databases?

Yes. Your agent can run listdatabases to discover all available environments in your team. From there, it passes the selected database ID to tools like getdatabaseschema to query specific tables.

Q: How does LangSmith help debug Ninox tools in a LangChain pipeline?

LangSmith traces the inputs and outputs of tools like updaterecord and deleterecord in real time. You see the exact payload sent by your agent and the database's response, making it easy to catch schema mismatches.

Run complex relational database workflows by chaining Ninox MCP tools directly into your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ninox MCP to LangChain

Create your Vinkius account to connect Ninox 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 Ninox with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map databases before executing LangChain chains

The `get_database_schema` tool exposes the exact structural layout of your Ninox tables to your LangChain agent. This prevents your pipeline from guessing field names or types, ensuring that subsequent steps have accurate schema definitions. By feeding this schema directly into the next step of your chain, your agent can dynamically prepare payloads for `list_records` without hardcoded parameters. You get predictable, structured data flows without manual configuration.

Build multi-step database update loops

This MCP Server lets your agent find a target row with `list_records` and immediately modify it using `update_record`. Each step executes as a discrete link in your LangChain pipeline, passing output variables forward. You can track every single transition, token cost, and tool payload in LangSmith to debug failing updates. If a script fails, the logs show exactly what went into `execute_ninox_script` during execution.

Execute custom formulas over an MCP connection

The `execute_ninox_script` tool allows your agent to run native calculations on your database server. This offloads heavy computation from your local Python environment directly to Ninox's backend engine. The agent processes the script's output, then uses `create_records` to write the computed results back to your tables. This keeps your data clean and synchronized across your entire operational stack.

Setup guide

Set up Ninox 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 Ninox 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({
    "ninox-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 Ninox 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 Ninox. 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 Ninox 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 Ninox MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the `MultiServerMCPClient` with the Vinkius endpoint URL, call `get_tools()`, and pass those tools directly to your agent constructor.

Yes. Your agent can run `list_databases` to discover all available environments in your team. From there, it passes the selected database ID to tools like `get_database_schema` to query specific tables.

LangSmith traces the inputs and outputs of tools like `update_record` and `delete_record` in real time. You see the exact payload sent by your agent and the database's response, making it easy to catch schema mismatches.

Yes. LangChain supports over 500 integrations. You can fetch data from an external API and write it directly to your tables using `create_records` in a single run.

Your relational database records and table schemas stay inside the secure V8 sandbox. Vinkius executes the calls ephemerally, ensuring no raw data is written to disk or exposed to external 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