How to Use the Determ MCP in LangChain

Q: How do I connect Determ to LangChain?

Install langchain-mcp-adapters and langgraph. You initialize a MultiServerMCPClient pointing to the Vinkius endpoint, then pass client.gettools() to your ReAct agent.

Q: How do I filter specific Determ mentions in LangChain?

Have your agent call searchmentionsbykeyword with specific search terms. The returned JSON feeds directly into the next link of your chain for further processing.

Build multi-step ReAct agents that monitor brand mentions and analyze sentiment using Determ and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Determ MCP to LangChain

Create your Vinkius account to connect Determ 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 Determ with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Media monitoring chains

LangChain agents can track brand visibility across the web using Determ's monitoring tools. You start by calling `list_monitoring_queries` to pull active topics right into your ReAct loop. From there, the agent decides which keywords need immediate attention. Once a topic is selected, the pipeline triggers `list_media_mentions` to grab the raw data. Developers can route these results through LLM chains to summarize daily press coverage or flag PR crises. Every tool invocation gets logged in LangSmith for full observability over token usage and latency.

Sentiment analysis pipelines via MCP Server

Connecting this MCP Server to your graph lets your agent measure public perception automatically. A standard chain might run `get_query_sentiment_summary` to grab the positive, neutral, and negative breakdown for a specific campaign. If the negative sentiment spikes, your agent steps in to investigate. It then fires off `search_mentions_by_keyword` to find exactly what people are complaining about. The output of that search becomes the input for a notification node that alerts your marketing team via Slack. Composable chains make this entire workflow modular and easy to debug.

Automated reporting agents

Your LangChain application can generate executive PR summaries on a schedule. Calling `list_analytics_reports` pulls the available dashboard data directly into the agent's context window. It reads the available metrics and decides how to format the final document. Next, the agent executes `list_top_media_sources` to identify which publications drive the most conversation. You can pass these lists into a vector store or write them out to a PDF generator. Multi-server aggregation means you can combine this Determ data with your CRM tools in the exact same chain.

Setup guide

Set up Determ 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 Determ 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({
    "determ-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 Determ 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 Determ. 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 Determ 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 Determ MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. You initialize a `MultiServerMCPClient` pointing to the Vinkius endpoint, then pass `client.get_tools()` to your ReAct agent.

Yes, LangSmith handles this natively. Every call to a tool like `get_mention_details` shows up as a distinct trace with exact latency and token metrics.

The server itself is stateless by default. You will need to use `client.session()` in your LangChain setup to maintain context across multiple API requests.

Have your agent call `search_mentions_by_keyword` with specific search terms. The returned JSON feeds directly into the next link of your chain for further processing.

It reads your brand monitoring queries, media mentions, and sentiment summaries. Vinkius runs this connection in an ephemeral V8 Isolate Sandbox, meaning your press data is never stored after the request completes.

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