How to Use the AgentOps (Agent Telemetry and Monitoring) MCP in Windsurf

Track your Cascade agent runs in real time and fix broken execution chains directly inside Windsurf.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentOps (Agent Telemetry and Monitoring) MCP to Windsurf

Create your Vinkius account to connect AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug Cascade runs with this MCP Server

The `get_trace` tool pulls the exact execution graph of your running agent so you can see where Cascade lost its way. When Cascade chains five steps together and fails on the fourth, you need to know which tool call broke the sequence. This tool feeds that raw execution path directly into your Windsurf chat. You don't have to open a browser tab to figure out why a tool call timed out or returned bad data.

Inspect agent steps with get_span

The `get_span` tool retrieves the granular details of a single operation within your larger agent workflow. Cascade uses this tool to check the inputs, outputs, and latency of specific LLM calls or tool executions. Having this telemetry inside Windsurf means Cascade can self-correct when it spots a slow or failed step. It reads the span data, adjusts its prompt, and retries without you intervening.

Audit project metrics directly in Windsurf

The `get_project` tool retrieves your high-level AgentOps workspace configuration and active monitoring settings. It gives Cascade the exact context of which environment it is running in and where it should send telemetry. Combine this with `get_trace_metrics` to let your agent analyze its own cost and success rates. Your agent reads the raw numbers, flags expensive runs, and helps you optimize your agent config on the fly.

Setup guide

Set up AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) payment history." If connected, Cascade will call the AgentOps (Agent Telemetry and Monitoring) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "agentops-agent-telemetry-and-monitoring-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 AgentOps. 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 AgentOps (Agent Telemetry and Monitoring) 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 AgentOps (Agent Telemetry and Monitoring) MCP in Windsurf

Open your Settings, head to Cascade, and find the MCP configuration UI to paste the server URL. Alternatively, you can edit your `~/.codeium/windsurf/mcp_config.json` file directly to add it under the `mcpServers` key. Once saved, Cascade immediately detects the new monitoring tools.

Yes, Cascade can autonomously query this MCP Server to inspect its own execution history. If a multi-step plan fails, Cascade calls `get_trace` to pull the execution graph, analyzes the failure point, and attempts a corrected run.

It gives Cascade direct access to execution latency and token usage metrics through `get_trace_metrics`. Cascade reads these numbers to identify slow prompts or bloated payloads, allowing you to refactor your prompts right in the IDE.

Your agent will typically fetch the high-level trace first using `get_trace` to find the bottleneck. Once Cascade pinpoints the slow or failed node, it targets that specific block using `get_span` to avoid token limit issues.

No, this server only handles AgentOps telemetry metadata, span identifiers, and project configurations. All data queries run through a secure Vinkius MCP Server instance, ensuring your raw LLM keys never leave your secure environment.

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