An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Datadog AI LLM Observability to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Bring your LLM telemetry directly into your AI agent's context.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Datadog.

  1. 01

    List events

    This capability pulls active event arrays to help you identify specific deployment or auth states.

  2. 02

    List incidents

    Use this to check the history of service disruptions and gateway issues.

  3. 03

    Query metrics

    This capability queries specific Datadog LLM observability metrics like token counts and latency.

  4. 04

    Submit series

    This capability extracts properties to drive active account logic.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Datadog.

  1. 05

    List AI monitors

    This capability retrieves cloud logging and vault limit information for your AI monitors.

  2. 06

    List dashboards

    Use this to find structured rules and billing data attached to your dashboards.

  3. 07

    List service accounts

    This capability identifies active arrays for parsing service account data.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Datadog.

  1. 08

    Search llm spans

    This capability searches for specific LLM spans and JSON payloads within your traces.

  2. 09

    Create event

    This capability inspects internal arrays to manage specific plan math.

  3. 10

    Create monitor

    Use this to set up or modify validations for churn flags and service thresholds.

Real work

What teams actually run

01

Debugging Model Latency

Ask your agent to check if a recent model switch caused a spike in response times.

02

Monitoring Token Spend

Have your agent pull dashboard data to see how much you've spent on specific providers today.

03

Auditing Prompt Logic

Use the agent to search through spans to find the exact prompt that caused a specific error.

04

Setting Up Alerts

Tell your agent to create a new monitor when LLM responses drop below a certain threshold.

Automate a task

Put Datadog to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Datadog works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Datadog to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

928ms average. Fast in production.

Datadog is checked daily against the live service.

Daily averagePeak 1444ms
Oct 3Today
Fastest day
868ms
Slowest day
1444ms
14-day trend
Slowing+62%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Datadog, so you can see the experience inside your AI.

It does not authenticate your account with Datadog. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Datadog Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_bWdhwHEHDioKsLvhV1Lvv7ec4t2gm8k5cIgCZeWx/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Datadog capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "datadog-ai-llm-observability-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_bWdhwHEHDioKsLvhV1Lvv7ec4t2gm8k5cIgCZeWx/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Datadog in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Datadog owners hand off.

Engineers and operations teams who need to keep a close eye on LLM performance without leaving their coding environment.

  • 01

    AI Engineers

    They ask the agent to monitor latencies and token costs during development.

  • 02

    MLOps Teams

    They use the agent to audit prompt logs and model performance across versions.

  • 03

    SREs

    They task the agent with setting up monitors and tracking service incidents.

  • 04

    FinOps

    They use the agent to analyze dashboards for AI infrastructure spending.

FAQ

Questions Datadog owners ask.

  • 01

    What AI clients can I use with this MCP?

    You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 02

    Do I need to host the MCP myself?

    No. Vinkius hosts and manages the MCP for you. You just connect your client and start using the capabilities.

  • 03

    What kind of data can my agent access?

    Your agent can access LLM metrics like token usage, latency, prompt traces, service incidents, and billing dashboards.

  • 04

    Is my Datadog data secure?

    Yes. Vinkius manages your credentials securely so you can connect your Datadog account to your AI client safely.

  • 05

    Can I create new monitors using my AI agent?

    Yes. You can use the create_monitor capability to set up new monitors for tracking AI service performance.

  • 06

    Can my agent check token usage for a specific LLM model?

    Yes. Use the 'query_metrics' capability with a query like 'avg:datadog.llm_observability.tokens{model:gpt-4}'. The agent will retrieve the numeric timeseries data directly from Datadog's metrics engine.

  • 07

    How do I search for specific prompt text in my logs?

    Use the 'search_llm_spans' capability. Provide a search query matching your prompt identifiers. The agent will pull the explicit REST maps capturing the literal prompt logic text from your Datadog logs.

  • 08

    Can I see if there are any active incidents affecting my AI services?

    Absolutely. The 'list_incidents' capability tracks outages and service disruptions in real-time. This allows your agent to identify exactly which external factors might be blocking your multi-agent orchestration pipelines.

Explore

More in AI Frontier

Suggestions

Connect Datadog to Claude, Cursor, ChatGPT & more