How to Use the Nimbata MCP in LangChain

Q: How do I initialize the Nimbata MCP Server in LangChain?

Install the adapter using pip install langchain-mcp-adapters langgraph. Then, point the MultiServerMCPClient to your hosted Vinkius endpoint and pass the tools directly to your agent constructor.

Q: Can a LangChain agent automatically create tracking numbers in Nimbata?

Yes. Your agent can use the createsource tool inside any active chain to provision a new campaign tracking source on the fly.

Q: How does LangChain monitor tool execution errors with Nimbata?

You use LangSmith to trace every single call to tools like getcallreport. It records the exact inputs, outputs, and latency of your API requests.

Q: Can I search call histories using this setup?

Yes, your agent can call searchcalls to filter past phone interactions by date, duration, or tracking number.

LangChain agents can now trace phone calls back to specific marketing campaigns using the Nimbata MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbata MCP to LangChain

Create your Vinkius account to connect Nimbata 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 Nimbata with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Call Origins in LangChain Chains

Stop guessing which ads actually make the phone ring. This MCP Server integration lets your LangChain agent run multi-step reasoning chains to link offline conversions to online spend. The agent checks active campaigns with `list_sources` and matches them against incoming calls using `list_calls`. You get complete observability over this entire pipeline through LangSmith tracing. If a tool call fails or latency spikes while pulling attribution data, you see it instantly. No more black boxes when connecting offline call events to your digital marketing stack.

Run Multi-Step Call Audits with LangGraph

Build autonomous workflows that don't just track calls but analyze what happened on them. Your agent can use `get_call_details` to find a specific call, then invoke `get_call_recording` to pull the audio for quality analysis. Because LangChain handles state across complex nodes, you can pass these audio files directly to transcription and sentiment chains. The agent decides the next step based on the call outcome, matching real-world conversations to digital campaign sources.

Connect Nimbata MCP Server Tools to 500+ APIs

LangChain lets you mix this call tracking server with your existing databases and CRMs. Your agent can call `get_source_report` to pull marketing performance data, then instantly write those metrics to a Postgres database or a Google Sheet. Setting this up takes a few lines of code. You initialize the client, call `get_tools()`, and pass them to your agent. This turns offline call tracking from an isolated silo into a core node in your existing data pipelines.

Setup guide

Set up Nimbata 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 Nimbata 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({
    "nimbata-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 Nimbata 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 Nimbata. 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 Nimbata 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 Nimbata MCP in LangChain

Install the adapter using `pip install langchain-mcp-adapters langgraph`. Then, point the `MultiServerMCPClient` to your hosted Vinkius endpoint and pass the tools directly to your agent constructor.

Yes. Your agent can use the `create_source` tool inside any active chain to provision a new campaign tracking source on the fly.

You use LangSmith to trace every single call to tools like `get_call_report`. It records the exact inputs, outputs, and latency of your API requests.

Yes, your agent can call `search_calls` to filter past phone interactions by date, duration, or tracking number.

Your call recordings and customer phone numbers never touch third-party LLMs unless you explicitly pass them in your chain. Vinkius runs the server in an ephemeral sandbox, securing your voice files and caller IDs during transport.

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