How to Use the Mention MCP in LangChain

Q: Can a LangChain chain run Mention searchmentionsbykeyword queries automatically?

Yes. You can build a chain where an agent calls searchmentionsbykeyword to find web discussions, then passes those results directly to a database or a Slack notification tool in the next step.

Build multi-step LangChain pipelines that track web mentions and alert your team the second your brand is discussed.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mention MCP to LangChain

Create your Vinkius account to connect Mention 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 Mention with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Brand Alerts in LangChain Chains

The `create_monitoring_alert` tool registers new search queries directly inside your LangChain agent's execution loop. Your agent uses this MCP tool to spin up targeted monitoring rules whenever a new product launch or competitor campaign is detected in your upstream database. Once configured, the agent runs `list_monitoring_alerts` to verify active tracking. It passes the resulting alert IDs to downstream steps, establishing a closed-loop system where your code reacts to web trends without manual setup.

Track Reputation Metrics via LangSmith

The `get_alert_statistics` tool pulls raw reach metrics and volume data directly into your LangChain runs. Because every tool call is traced in LangSmith, you can audit exactly how your agent evaluates sentiment trends and inspect the raw payload latency. Your agent uses `list_recent_mentions` to pull the latest web hits, filtering out noise before passing clean text to a summarization chain. You see the exact input-output mapping for every brand mention, making it easy to debug why a specific post triggered a high-priority alert.

Triage Live Mentions in Your LangChain MCP Server

The `get_mention_content` tool pulls the full text of any web or social post your agent flags. Your LangChain agent evaluates this content, deciding whether to run `favorite_mention` for positive feedback or flag it for immediate human review. To keep your queue clean, the agent uses `mark_mention_as_read` after processing each item. This keeps your active workspace uncluttered while ensuring your agent never processes the same social post twice during subsequent runs.

Setup guide

Set up Mention 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 Mention 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({
    "mention-alternative-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 Mention 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 Mention. 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 Mention 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 Mention MCP in LangChain

Use the LangChain MCP adapter to convert the tools. Initialize the client with your Vinkius endpoint, call `get_tools()`, and feed the resulting list directly into your agent constructor.

Yes. You can build a chain where an agent calls `search_mentions_by_keyword` to find web discussions, then passes those results directly to a database or a Slack notification tool in the next step.

LangChain catches API errors through its standard run managers. If `list_recent_mentions` fails due to network issues, your chain can retry the call or fall back to a cached list of alerts.

This MCP Server runs on standard SSE (Server-Sent Events) managed by Vinkius. Your python or typescript application connects via HTTP, meaning you do not need to manage local subprocesses or raw stdio pipes.

Vinkius runs the MCP Server in an isolated V8 sandbox. Your API keys, configured alert queries, and raw mention texts are never stored on our servers; they transit through an ephemeral, zero-trust connection directly to your agent.

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