How to Use the Checkly MCP in Google ADK

Q: Can Google ADK execute Checkly tests?

Your agent runs the triggercheckrun tool to force an immediate execution. This works perfectly for validating deployments deployed via Google Cloud Build. Gemini evaluates the test output to determine if the rollout succeeded.

Q: Does Google ADK read my Checkly account metadata?

Yes, the getchecklyaccountinfo tool retrieves your core organization details. The agent uses this to format reports correctly. It helps when managing multiple environments across different GCP projects.

Connect the Checkly MCP server to your Google ADK agents to cross-reference API latency with BigQuery telemetry data.

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 Google ADK

Create your Vinkius account to connect Checkly to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK latency analysis

Enterprise systems generate massive amounts of telemetry. Exposing `get_check_performance_metrics` allows your Gemini agent to pull Checkly response times directly into its context window. It can then correlate those latency spikes with infrastructure logs stored in BigQuery. Long-context reasoning makes this incredibly powerful. You can feed weeks of performance data into the model at once. The agent digests the entire timeline and identifies subtle degradation patterns that basic alerting misses.

Audit alert configurations

Missing a critical notification usually means someone misconfigured a webhook. Running `list_checkly_alert_channels` gives your agent a complete map of every Slack, Email, and PagerDuty integration in your account. It cross-checks this list against your official routing rules. Finding gaps takes seconds instead of hours. The agent uses `list_check_groups` to verify that high-priority monitor clusters actually have active alerting attached. If a production group lacks a PagerDuty channel, the agent flags it immediately.

Monitor heartbeat jobs

Cron jobs fail silently when servers crash. Calling `list_checkly_heartbeats` pulls the exact status of your scheduled tasks into the agent's memory. It checks whether your database backups and data syncs actually fired on time. Connecting this to Vertex AI pipelines creates a self-healing loop. If a heartbeat drops, the agent can trigger a remediation script on Google Cloud. The MCP server handles the Checkly API communication while you focus on the logic.

Setup guide

Set up Checkly MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Checkly tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Checkly_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Checkly tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate an McpToolset using StreamableHttpServerParameters and your Vinkius URL. Pass that toolset to your LlmAgent. You can optionally restrict exposed tools using the tool_names filter.

Your agent runs the trigger_check_run tool to force an immediate execution. This works perfectly for validating deployments deployed via Google Cloud Build. Gemini evaluates the test output to determine if the rollout succeeded.

Yes, the get_checkly_account_info tool retrieves your core organization details. The agent uses this to format reports correctly. It helps when managing multiple environments across different GCP projects.

The framework allows you to pass a specific list of tool names during initialization. Limiting the agent to just read-only commands prevents accidental test triggers. This keeps your enterprise deployments secure.

The MCP server operates inside a zero-trust V8 isolate. Your PagerDuty routing keys, Slack webhook URLs, and internal endpoint addresses remain strictly in memory. Vinkius destroys the sandbox the moment the Gemini 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