How to Use the NinjaCat MCP in LangChain

Q: How do I connect the NinjaCat MCP to my LangChain agent?

Install langchain-mcp-adapters. Then initialize a MultiServerMCPClient pointing to the NinjaCat MCP Server URL and pass the tools to your agent.

Q: Can my LangChain pipeline download a NinjaCat report directly?

Yes. The agent uses getreportdownloadurl to grab the secure link. You can then write a custom LangChain tool to fetch the actual file contents from that URL.

Q: How do I track multiple agency campaigns in LangChain with NinjaCat?

Call listagencycampaigns to get the active roster. Your LangChain agent can iterate over that array and trigger separate analysis chains for each campaign.

Build multi-step marketing reporting chains in LangChain with live NinjaCat data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NinjaCat MCP to LangChain

Create your Vinkius account to connect NinjaCat 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 NinjaCat with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Agency Accounts in LangChain

The `list_data_sources` and `list_data_accounts` tools pull your active integration endpoints directly into your LangChain agent's context. You don't have to guess if a Google Ads account is actually connected before running a query. The agent fetches the exact IDs and maps them to your current agency setup. Output from those tools feeds straight into the next step of your chain. Your agent can grab the data sources, identify the target client, and prep the environment for a deeper dive into specific campaigns without breaking stride.

NinjaCat MCP Server Report Chains

Your LangChain setup uses `list_reports` and `get_report_history` to track exactly what marketing documents went out and when. If an account manager needs the latest performance deck, the agent checks the execution log first. It sees if the report actually ran before trying to fetch it. Once the agent confirms the run, it calls `get_report_download_url`. You get the exact URL passed down the chain. The agent can then hand that link off to an email tool or drop it into a Slack channel, completely automating the weekly client update.

Dynamic Campaign Lookups

Give your ReAct agent access to `list_advertisers` and `get_advertiser` to pull specific client metadata on the fly. When a prompt asks about a specific brand, the agent searches the advertiser list, finds the match, and pulls the detailed record. It combines that context with `list_agency_campaigns`. Now your LangChain pipeline has the full picture—the client details and their active marketing pushes—ready to process or summarize. You trace the whole execution path, including token usage and latency, right inside LangSmith.

Setup guide

Set up NinjaCat 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 NinjaCat 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({
    "ninjacat-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 NinjaCat 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 NinjaCat. 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 NinjaCat 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 NinjaCat MCP in LangChain

Install `langchain-mcp-adapters`. Then initialize a `MultiServerMCPClient` pointing to the NinjaCat MCP Server URL and pass the tools to your agent.

Yes. The agent uses `get_report_download_url` to grab the secure link. You can then write a custom LangChain tool to fetch the actual file contents from that URL.

Every tool call is automatically traced. You'll see the exact inputs and outputs for `list_agency_campaigns` or `get_advertiser` in your LangSmith dashboard.

Call `list_agency_campaigns` to get the active roster. Your LangChain agent can iterate over that array and trigger separate analysis chains for each campaign.

The server reads your campaign metadata and report URLs, passing them directly to your local LangChain environment. Vinkius runs the server in an ephemeral V8 isolate sandbox, meaning your API tokens and client records vanish the second the session ends.

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