How to Use the Gatus (Health Dashboard) MCP in Windsurf

Q: Can Cascade automatically monitor services with Gatus (Health Dashboard) in Windsurf?

Yes. Cascade can run an autonomous loop using listendpoints to watch your services. If a service goes down, the agent alerts you and starts debugging the relevant local files.

Q: How do I configure the Gatus (Health Dashboard) MCP Server inside Windsurf?

Open your mcpconfig.json file in your Codeium directory. Add the server under the mcpServers key with your Vinkius access token, then refresh the MCP panel.

Q: What metrics can Cascade pull from this server?

Cascade uses getmetrics to pull raw Prometheus-compatible data. It can also use getendpointstats to get average latency, success rates, and uptime percentages.

Cascade chains Gatus health checks autonomously inside Windsurf to fix failing endpoints before your pager goes off.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gatus (Health Dashboard) MCP to Windsurf

Create your Vinkius account to connect Gatus (Health Dashboard) to Windsurf 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 Gatus (Health Dashboard) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track live endpoint state in Windsurf

The `list_endpoints` tool fetches every monitored service and its current status directly into your editor via our MCP Server. Cascade reads this list, spots any degraded services immediately, and plans the exact debug sequence without waiting for your input. If an endpoint is failing, the agent automatically triggers `get_endpoint_health` to retrieve the exact error code and recent results. You see the raw response payload and the exact point of failure right inside the chat panel.

Debug latency spikes with this MCP Server

This MCP Server lets Cascade query `get_endpoint_stats` to isolate slow response times and packet loss on your services. The agent pulls the historical performance metadata, compares it against current latency, and pinpoints where the slowdown started. Instead of jumping to an external dashboard, Cascade uses these stats to find patterns. It can correlate a sudden latency spike with recent code changes you made in the workspace.

Extract raw Prometheus data via Cascade

The `get_metrics` tool pulls raw Prometheus-compatible metrics directly from your Gatus server. Cascade uses this raw data to build a clear picture of long-term infrastructure trends right in your IDE. You can ask Cascade to write a custom script that parses these metrics. The agent writes the parsing logic, tests it against the live data stream, and saves it to your workspace.

Setup guide

Set up Gatus (Health Dashboard) MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Gatus (Health Dashboard) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Gatus (Health Dashboard) payment history." If connected, Cascade will call the Gatus (Health Dashboard) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "gatus-health-dashboard-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Gatus. 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 Gatus (Health Dashboard) 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 Gatus (Health Dashboard) MCP in Windsurf

Windsurf connects to the server via the Cascade panel. When an endpoint fails, Cascade calls `get_endpoint_health` to get the error details, reads your local code, and suggests a fix.

Yes. Cascade can run an autonomous loop using `list_endpoints` to watch your services. If a service goes down, the agent alerts you and starts debugging the relevant local files.

Open your `mcp_config.json` file in your Codeium directory. Add the server under the `mcpServers` key with your Vinkius access token, then refresh the MCP panel.

Cascade uses `get_metrics` to pull raw Prometheus-compatible data. It can also use `get_endpoint_stats` to get average latency, success rates, and uptime percentages.

Yes. Vinkius runs this server in an isolated V8 sandbox. Only the raw health status and metrics retrieved via `get_endpoint_health` are passed to your local Windsurf client.

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