How to Use the Keen MCP in LangChain

Q: Can LangChain execute saved Keen queries automatically?

Yes, the agent calls listsavedqueries to find existing setups. It then uses the query definitions to retrieve data without manual coding.

Q: How does LangChain handle event streaming to Keen?

The agent uses recordevent to post metrics during run execution. Each event records instantly, and you can trace the execution path in LangSmith.

Feed live event metrics directly into your LangChain decision loops with the Keen 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 Keen MCP to LangChain

Create your Vinkius account to connect Keen 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 Keen with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step event processing chains in LangChain

The `record_event` tool lets your agent pipe raw telemetry directly into your Keen collections as steps execute. When a user runs a query, the agent intercepts the output, passes it to the next link in your chain, and keeps the context moving. You track everything via LangSmith. Every call to the MCP server shows up in your tracing dashboard with exact latency and token counts.

Let your agent decide how to query Keen metrics

The `list_saved_queries` tool gives your LangChain agent immediate access to pre-configured reports. Instead of guessing schema structures, the agent inspects existing setups and selects the exact query needed. If a saved query doesn't exist, the agent falls back to runtime calculations. It runs `average_property` or `count_unique` to pull fresh numbers, resolving complex questions dynamically.

Dynamically inspect collection schemas on the fly

The `list_collections` tool reveals your event database structure to the agent. This allows the model to map incoming user questions to the correct event streams without manual routing. Once the agent identifies the correct collection, it uses `select_unique` to verify property values. You get precise answers derived directly from live telemetry.

Setup guide

Set up Keen 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 Keen 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({
    "keen-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 Keen 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 Keen. 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 Keen 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 Keen MCP in LangChain

Use the MultiServerMCPClient from the LangChain MCP adapters package. Point it to your Vinkius endpoint, fetch the tools, and pass them directly to your agent constructor.

Yes, the agent calls `list_saved_queries` to find existing setups. It then uses the query definitions to retrieve data without manual coding.

The agent uses `record_event` to post metrics during run execution. Each event records instantly, and you can trace the execution path in LangSmith.

No, Vinkius handles the credentials on its secure gateway. Your code only needs a single Vinkius token to execute tools like `get_project_details`.

Vinkius runs the adapter in an isolated V8 sandbox. Your event payloads and API keys never touch persistent external storage during execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.