How to Use the Checkly MCP in LangChain

Q: How do I connect Checkly to LangChain?

Install langchain-mcp-adapters via pip. Initialize a MultiServerMCPClient pointing to your Vinkius endpoint. Call client.gettools() and pass the resulting array to your ReAct agent.

Q: Can a LangChain agent trigger a Checkly run?

Yes. The agent uses the triggercheckrun tool. It passes the specific check ID to force an immediate execution, which is perfect for automated remediation chains.

Q: How do I list my heartbeats?

Your agent calls listchecklyheartbeats. This returns the current status and configuration of all your cron monitors.

Q: Is my Checkly account metadata secure?

When your agent calls getchecklyaccountinfo, the data routes through an ephemeral V8 Isolate sandbox on Vinkius. The container processes the organization details and tears itself down immediately. No persistent storage touches your API keys or infrastructure layout.

Build composable monitoring chains that fetch Checkly metrics and trigger reruns directly through your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Checkly MCP to LangChain

Create your Vinkius account to connect Checkly 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 Checkly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run API Checks via LangChain MCP Server

The `list_checkly_checks` tool pulls your entire API and browser monitoring suite into your agent's context. Your LangChain agent reads the current status of every endpoint monitor before deciding what to do next. If a specific service looks suspicious, the chain automatically passes that ID to `get_check_details` for a deeper look. You build multi-step reasoning pipelines right here. An agent sees a failing check, pulls the exact failure reason, and immediately fires `trigger_check_run` to see if the issue persists. LangSmith traces every step, showing you exactly how many tokens the agent burned while debugging your staging environment.

Chain Performance Data into Diagnostics

Fetching response times happens through the `get_check_performance_metrics` tool. Your ReAct agent pulls latency data for the last hour and compares it against historical baselines. When a spike happens, the agent knows exactly which API endpoint caused the slowdown. Connecting this data to other tools makes it powerful. You might write a chain that grabs Checkly metrics, queries your database for active connections, and summarizes the correlation. The output of the Checkly tool feeds directly into your next diagnostic step without manual intervention.

Audit Cron Monitors and Alert Channels

The `list_checkly_heartbeats` tool grabs the status of every scheduled cron job you track. Your agent identifies silent failures where a background job stopped pinging Checkly. It then uses `list_checkly_alert_channels` to verify who actually got notified about the outage. This setup prevents configuration drift. A scheduled LangChain script can pull your current alert routing, check it against your team's on-call schedule via another API, and flag mismatches. You stop clicking through dashboards and let the agent verify your safety nets.

Setup guide

Set up Checkly 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 Checkly 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({
    "checkly-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 Checkly 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 Checkly. 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 Checkly 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 Checkly MCP in LangChain

Install `langchain-mcp-adapters` via pip. Initialize a `MultiServerMCPClient` pointing to your Vinkius endpoint. Call `client.get_tools()` and pass the resulting array to your ReAct agent.

Yes. The agent uses the `trigger_check_run` tool. It passes the specific check ID to force an immediate execution, which is perfect for automated remediation chains.

Every tool invocation gets logged automatically. You see the exact inputs sent to Checkly and the raw JSON response returned. This makes debugging your agent's logic straightforward.

Your agent calls `list_checkly_heartbeats`. This returns the current status and configuration of all your cron monitors.

When your agent calls `get_checkly_account_info`, the data routes through an ephemeral V8 Isolate sandbox on Vinkius. The container processes the organization details and tears itself down immediately. No persistent storage touches your API keys or infrastructure layout.

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