How to Use the MOBIDI MCP in LangChain

Q: Can a LangChain agent run MOBIDI reports autonomously?

Yes. The agent uses tools like listreports to see what is available, then executes the chosen one via executereport. It reads the output directly to make campaign decisions.

Run real-time mobile ad bidding and pull campaign analytics directly inside your LangChain multi-step reasoning chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MOBIDI MCP to LangChain

Create your Vinkius account to connect MOBIDI 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 MOBIDI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run real-time bidding chains in LangChain

You need your agents to react to performance changes fast. By linking this MCP Server to your LangChain setup, your agent can check API connectivity using `check_mobidi_status` and immediately adjust bid records based on live performance data. It does not require hardcoding logic for every variable. The agent decides when to trigger `update_record` to adjust budget caps and when to clean up old targets using `delete_record`. Every single operation runs as a discrete step in your graph, letting you trace exact inputs and outputs through LangSmith.

Build automated ad reporting loops with LangChain

Pulling campaign data manually is a waste of time. This MCP Server lets your chain pull structured performance reports using `execute_report` and feed that raw data directly into the next LLM node for analysis. You get a closed loop where the agent reads the numbers and acts on them. The chain can inspect the available metrics using `get_report` and list all existing configurations via `list_reports`. This means your agent can autonomously figure out which reports exist, run them, and format the results for your team without manual scripting.

Query and count campaign records dynamically

Large mobile campaigns generate thousands of targeting groups. Your LangChain agent can use MCP tools like `get_record_count` to check database volume before running heavy queries. This prevents your LLM from hitting token limits or pulling unnecessary bulk data. When details are missing, the agent uses `get_record_by_id` to pinpoint a specific campaign profile or queries broader lists via `list_records`. It keeps your context window clean and your execution costs low.

Setup guide

Set up MOBIDI 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 MOBIDI 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({
    "mobidi-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 MOBIDI 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 MOBIDI. 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 MOBIDI 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 MOBIDI MCP in LangChain

Install the adapter package and initialize the multi-server client with the Vinkius endpoint. You then fetch the tools and pass them directly to your agent constructor.

Yes. The agent uses tools like `list_reports` to see what is available, then executes the chosen one via `execute_report`. It reads the output directly to make campaign decisions.

The server communicates directly with the mobile ad API. To avoid hitting limits, design your LangChain graph to check `get_record_count` before pulling massive datasets.

No. The adapter handles schema translation automatically. Tools like `list_entity_types` return clean JSON that your chains can read without extra code.

All campaign records, bidding parameters, and app install metrics remain inside an isolated V8 sandbox on Vinkius. No third party can access your API tokens or raw performance data.

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