How to Use the Checkly MCP in AutoGen

Q: How do I configure Checkly for AutoGen?

Install autogen-extmcp. Use mcpservertools with StreamableHttpServerParams pointing to your endpoint. The McpToolAdapter handles all schema conversions automatically for your AssistantAgent.

Q: How does AutoGen read Checkly account data?

Agents use the getchecklyaccountinfo tool. They read your organization limits and metadata to understand the context of your monitoring setup before making decisions.

Q: Do the agents know which alert channels are active?

Yes. Calling listchecklyalertchannels returns your current routing configuration. Agents use this to verify that critical monitors actually page a human.

Q: What happens to my heartbeat monitor data?

When an agent runs listchecklyheartbeats, the Vinkius platform processes the request in memory. The connection uses single-endpoint token authentication. Your cron schedule data is wiped the millisecond the HTTP response completes.

Give your AutoGen agents the ability to debate API performance and trigger Checkly test runs autonomously.

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 AutoGen

Create your Vinkius account to connect Checkly to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Testing via AutoGen MCP Server

The `trigger_check_run` tool lets your agents force an immediate execution of any API or browser monitor. A QA agent notices a deployment event and immediately fires off a critical checkout test. If it fails, the agent flags the issue to the deployment agent, sparking a debate on whether to roll back the release. Digging into the failure requires the `get_check_details` tool. The debugging agent pulls the exact response payload and assertion errors. It presents this evidence to the rest of the swarm, forcing consensus based on actual API responses rather than assumptions.

Multi-Agent Performance Diagnostics

Agents fetch latency statistics using the `get_check_performance_metrics` tool. A performance-focused agent monitors these numbers constantly. When response times creep up, it challenges the database agent to explain the slowdown, using hard metrics from Checkly as proof. Organizing the investigation starts with `list_check_groups`. The swarm identifies which cluster of services is degrading. They isolate the problem to a specific microservice group before diving into individual endpoint metrics.

Audit Cron Jobs and Routing Rules

The `list_checkly_heartbeats` tool pulls the status of all your scheduled background tasks. A reliability agent scans this list looking for jobs that missed their ping. It alerts the operations agent, who then decides if manual intervention is necessary. Verifying who gets notified is handled by `list_checkly_alert_channels`. A security agent can audit your PagerDuty and Slack hooks to ensure critical failures escalate to the right people. If a channel is missing, the swarm documents the gap.

Setup guide

Set up Checkly MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Checkly tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Checkly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Checkly data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Checkly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Checkly data")
    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 AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your endpoint. The `McpToolAdapter` handles all schema conversions automatically for your `AssistantAgent`.

Multiple agents can debate a course of action before one invokes `trigger_check_run`. You might have a senior agent approve the test execution proposed by a junior debugging agent.

Agents use the `get_checkly_account_info` tool. They read your organization limits and metadata to understand the context of your monitoring setup before making decisions.

Yes. Calling `list_checkly_alert_channels` returns your current routing configuration. Agents use this to verify that critical monitors actually page a human.

When an agent runs `list_checkly_heartbeats`, the Vinkius platform processes the request in memory. The connection uses single-endpoint token authentication. Your cron schedule data is wiped the millisecond the HTTP response 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