How to Use the Datadog AI (LLM Observability) MCP in VS Code Copilot
Let your whole team query Datadog LLM metrics and incidents directly from Copilot Chat in VS Code.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Datadog AI (LLM Observability) MCP to VS Code Copilot
Create your Vinkius account to connect Datadog AI (LLM Observability) to VS Code Copilot and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Standardize LLM Monitoring for Your Team
Get your whole team on the same page. A tech lead adds this MCP Server to the `.vscode/mcp.json` file and commits it to the repo. Now every engineer on the team has the same tools for querying Datadog in their editor. This ensures consistency. When anyone on the team asks Copilot, "How many tokens did our 'billing-parser' model use yesterday?", they all get the answer the same way, using the same `query_metrics` tool. No one needs to hunt for dashboards or ask for a link.
Bring Observability into Code Reviews
Imagine you're reviewing a pull request that changes an LLM prompt. Right in VS Code, you can ask Copilot to `search_llm_spans` for examples of the old prompt's performance. You can also `list_incidents` related to that model to see if it's been causing problems. This makes code reviews data-driven. You're not guessing if a change is an improvement. You're pulling hard numbers and logs from Datadog directly into the context of the code change, right inside your editor.
Manage Monitors via Copilot Agent
Your team can manage Datadog resources without leaving the editor. Ask the Copilot Agent, "Create a monitor to alert when `datadog.llm_observability.tokens` exceeds 1 million for production." The agent will use the `create_monitor` tool to get it done. You can also use `list_ai_monitors` or `list_dashboards` to get a quick overview of your current setup, all from the Copilot Chat panel. This MCP server is built for team workflows, not just solo developers.
Set up Datadog AI (LLM Observability) MCP in VS Code Copilot
Prerequisites
- VS Code 1.99 or later with GitHub Copilot extension
- Active Vinkius subscription with a valid endpoint token
- 1
Open MCP configuration
Open the Command Palette (
Cmd+Shift+P/Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create.vscode/mcp.jsonin your workspace. - 2
Add the Datadog AI (LLM Observability) MCP
Paste the JSON snippet shown on the right into your
.vscode/mcp.json. Replace[YOUR_TOKEN_HERE]with your endpoint token from cloud.vinkius.com. - 3
Switch to Agent mode
Open Copilot Chat (
Cmd+Shift+I/Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes. - 4
Verify the connection
In the Copilot Chat input, type
#to list available tools. You should see the Datadog AI (LLM Observability) tools listed. Try asking: "List my recent Datadog AI (LLM Observability) transactions" and Copilot will invoke them automatically.
{
"mcpServers": {
"datadog-ai-llm-observability-mcp": {
"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}
}
}Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Datadog. 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.
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 Datadog AI (LLM Observability) MCP in VS Code Copilot
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Datadog AI (LLM Observability) MCP today
We host it, we monitor it, we maintain it. You just paste one token.
