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

Q: How do I install AgentOps (Agent Telemetry and Monitoring) in Claude Code?

Run claude mcp add --transport http agentops -- in your terminal. This command adds the server to your /.claude.json configuration file, making the tools instantly available in your next terminal session.

Q: How does AgentOps (Agent Telemetry and Monitoring) help Claude Code debug cron jobs?

If an automated script fails, Claude Code uses gettrace to pull the execution history of that specific run. It parses the trace output in the terminal, identifies the bug, and can even patch your script on the fly.

Query AgentOps traces and debug production agent telemetry directly from your terminal with Claude Code.

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 Claude Code

Create your Vinkius account to connect AgentOps (Agent Telemetry and Monitoring) to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect active agent traces from the command line

The `get_trace` tool retrieves full execution histories for specific agent runs directly into your shell session. Claude Code uses this tool to pipe raw execution graphs into other CLI utilities or grep for specific error codes. This is ideal for SREs who need to debug live agent failures during an on-call incident. You don't need a heavy web UI; just ask your command-line agent to fetch the trace and locate the failing step.

Analyze execution spans with Claude Code

The `get_span` tool extracts detailed timing, input arguments, and output payloads for any single step in your workflow. Claude Code calls this tool to dissect complex agent behaviors without leaving the terminal. By getting raw span details, you can quickly write shell scripts that parse execution bottlenecks. Your agent can automate this, scanning dozens of spans to find the exact database query or API call that slowed down your system.

Monitor project health via this MCP Server

The `get_project` tool pulls your AgentOps project configuration, allowing Claude Code to verify your monitoring setup across staging and production. It ensures your CI/CD pipelines are pointing to the correct telemetry environments. You can combine this with `get_trace_metrics` to run automated performance audits. Pipe the output to local files or use it in cron jobs to alert your team when agent success rates dip below your threshold.

Setup guide

Set up AgentOps (Agent Telemetry and Monitoring) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see agentops-agent-telemetry-and-monitoring-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest AgentOps (Agent Telemetry and Monitoring) transactions." It will automatically discover and invoke the available AgentOps (Agent Telemetry and Monitoring) tools.

Terminal

claude mcp add --transport http agentops-agent-telemetry-and-monitoring-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "agentops-agent-telemetry-and-monitoring-mcp": {
      "type": "url",
      "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 Claude Code

Run `claude mcp add --transport http agentops -- ` in your terminal. This command adds the server to your `~/.claude.json` configuration file, making the tools instantly available in your next terminal session.

Yes, you can run Claude Code headlessly in GitHub Actions or Docker containers to query this MCP Server. It lets you write automated scripts that pull trace metrics and fail builds if agent accuracy drops.

If an automated script fails, Claude Code uses `get_trace` to pull the execution history of that specific run. It parses the trace output in the terminal, identifies the bug, and can even patch your script on the fly.

It uses the HTTP transport protocol managed by Vinkius. This allows Claude Code to securely connect to the MCP Server over an encrypted connection without needing local node installations.

Your credentials are encrypted and managed directly by the Vinkius platform. Claude Code accesses the tools through an ephemeral, zero-trust connection, ensuring your telemetry keys are never exposed in plaintext logs.

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