Skip to content
Vinkius

Datadog AI (LLM Observability) Connector for AI agents.

10 live capabilities

Track token costs and monitor production model latency in real time.

Live agent request Datadog AI (LLM Observability) / Connector

Waiting for input…

AI Agent

Why people use Datadog AI (LLM Observability)

Datadog AI (LLM Observability) for Real-Time Token Cost Tracking

This Connector puts that data where you're already working. You just ask your agent to pull the metrics, and it gives you the numbers immediately. You get a clear picture of your model's performance without the context switching.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • Visual Studio Code
  • Windsurf

What Vinkius changes

You get a conversational window into your Datadog LLM telemetry without leaving your primary workspace.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

  1. Real-world use case 01

    Debugging a slow prompt

    An AI Engineer notices a specific request is lagging.

  2. Real-world use case 02

    Monthly cost auditing

    A FinOps analyst wants to know the monthly spend.

  3. Real-world use case 03

    Identifying production errors

    An MLOps person sees a spike in errors.

Complete set · 10capabilities

The complete Datadog AI (LLM Observability) capability set.

These are the exact actions your AI can choose when you ask it to work with Datadog AI (LLM Observability).

Capability set01 / 03

01—04

4 capabilities in this set.

Part of 10 available through Datadog AI (LLM Observability).

  1. 01 Capability

    List dashboards

    See all attached rules and active billing widgets. This gives you a clear view of your spending and rules.

  2. 02 Capability

    List events

    Find active arrays related to native Gateway authentication. It helps you track specific deployment events.

  3. 03 Capability

    List incidents

    Run automated checks to route Gateway history. This helps you see active outages and disruptions.

  4. 04 Capability

    Search llm spans

    Generate JSON payloads for customer bindings. Use this to pull specific prompt logs and traces.

Capability set02 / 03

05—07

3 capabilities in this set.

Part of 10 available through Datadog AI (LLM Observability).

  1. 05 Capability

    List ai monitors

    View cloud logging for Vault limits. This lets you see your active AI monitoring status.

  2. 06 Capability

    Query metrics

    Find CRM records inside the Datadog platform. Use this to pull token counts and latency numbers.

  3. 07 Capability

    Submit series

    Extract properties that drive account logic. This helps you track specific property-driven logic.

Capability set03 / 03

08—10

3 capabilities in this set.

Part of 10 available through Datadog AI (LLM Observability).

  1. 08 Capability

    List service accounts

    Identify active arrays for hold parsing. Use this to manage your service accounts and permissions.

  2. 09 Capability

    Create event

    Inspect internal arrays to handle specific Plan Math scenarios. This helps you manage complex logic events.

  3. 10 Capability

    Create monitor

    Set up validations to catch and flag high churn signals. Use this to create automated alerts for your AI.

Set up in minutes

One URL. Then ask Datadog AI (LLM Observability) to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Datadog AI (LLM Observability) from the conversation.

Choose your client

Live preview
Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP
https://edge.vinkius.com/vk_preview_bWdhwHEHDioKsLvhV1Lvv7ec4t2gm8k5cIgCZeWx/mcp
  1. Step 01

    Open Connectors

    In Claude Web or Claude Desktop, open Settings and choose Connectors.

  2. Step 02

    Add the URL

    Choose Add custom connector, name it Datadog AI (LLM Observability), and paste the URL above.

  3. Step 03

    Turn it on in chat

    Select +, open Connectors, and enable Datadog AI (LLM Observability) for the conversation.

Where the request belongs

Work Datadog can move forward.

Built around the request

This is for the engineers and ops folks who are tired of jumping between their IDE and a browser just to see if their production AI is actually working or breaking the bank.

01

AI Engineer

Debugging production prompts and checking latency on a Tuesday afternoon without leaving the code.

02

MLOps Team Member

Auditing logs to see why a specific model version is drifting or failing in the wild.

03

SRE

Setting up automated alerts for when AI services hit a bottleneck or experience an outage.

04

FinOps Analyst

Tracking how much OpenAI or Anthropic is costing the company each month across different projects.

Build the capability set

Add more capabilities.

Each Connector adds new actions and data without changing how you work.

Browse Connectors
New Relic AI (LLM Observability) logo
01 10 capabilities

New Relic AI (LLM Observability)

Monitor and audit LLM telemetry via New Relic AI. track token costs, p95 latency, and user feedback.

View Connector
LangSmith logo
02 3 capabilities

LangSmith

Observability and evaluation platform for LLM applications. monitor traces, debug agent runs, and track performance metrics across your AI stack.

View Connector
Helicone (LLM Observability) logo
03 10 capabilities

Helicone (LLM Observability)

Monitor LLM usage via Helicone. track requests, analyze costs, measure latency, and manage prompts.

View Connector
LangSmith (LLM Observability & Hub) logo
04 6 capabilities

LangSmith (LLM Observability & Hub)

Monitor LLM apps via LangSmith. track traces, audit prompt templates, and manage evaluation datasets.

View Connector
Langfuse (LLM Tracing & Evals) logo
05 10 capabilities

Langfuse (LLM Tracing & Evals)

Monitor LLM apps via Langfuse. track traces, manage prompt templates, and audit evaluation scores.

View Connector
Portkey logo
06 10 capabilities

Portkey

AI gateway observability: monitor logs, costs, and manage LLM configurations via agents.

View Connector

Bring your own AI

Change the model, client or framework. Keep Datadog connected.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • VS Code
  • Windsurf
  • ZCode
  • Cline
  • Zed
  • Continue
  • Kiro
  • Roo Code
  • Zencoder
  • Goose
  • Void
  • Augment Code
  • Amp
  • Qodo
  • Tabnine
  • Pieces
  • Sourcegraph Cody
  • JetBrains
  • Warp
  • Amazon Q
  • Antigravity
  • BoltAI
  • Raycast
  • Jan
  • LM Studio
  • AnythingLLM
  • Open WebUI
  • Msty
  • Cherry Studio
  • LibreChat
  • TypingMind
  • Chorus
  • 5ire
  • n8n
  • LangChain
  • LlamaIndex
  • CrewAI
  • Vercel AI SDK

Before you connect

Questions about Datadog.

The practical details behind the request, access and result.

Can the Datadog AI (LLM Observability) MCP show me how much I'm spending on OpenAI?

Yes, it can pull your spending metrics directly. You can ask your agent to show you costs across different providers like OpenAI or Anthropic to see where your budget is going.

How do I use Datadog AI (LLM Observability) to find specific prompt logs?

You can simply ask your agent to search for specific keywords or errors within your prompt logs. It will pull the relevant spans and show you the exact logic and responses.

Can I set up alerts for my LLM using Datadog AI (LLM Observability)?

Absolutely. You can ask your agent to create new monitors that trigger alerts when your LLM latency spikes or when your token usage hits a certain threshold.

Does the Datadog AI (LLM Observability) MCP work with Cursor?

Yes, it works with any MCP-compatible client, including Cursor, Claude, and Windsurf. Once connected, your agent can access all your Datadog LLM telemetry.

How does Datadog AI (LLM Observability) help with model latency?

It allows you to query real-time latency metrics instantly. You can quickly identify which models are underperforming without having to manually filter through complex dashboards.

Can I see my deployment history with Datadog AI (LLM Observability)?

Yes, you can pull textual deployment marks. This helps you see exactly when you switched models or pushed new updates to your AI infrastructure.

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.

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.

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.

One connection away

Give your agent a direct line to Datadog.

Connect Datadog once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available