An astronaut overseeing a futuristic data hub

Connect Opencost K8s Cost to ChatGPT, Claude and Gemini

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. Get real-time visibility into your cluster spending through your AI agent.

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 · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through OpenCost.

  1. 01

    Set log level

    Adjusts the OpenCost log level while the system is running.

  2. 02

    Get assets

    Retrieves cost data for specific physical infrastructure like nodes, disks, and load balancers.

  3. 03

    Get cloud cost

    Pulls billing data directly from cloud provider reports to help you reconcile K8s spend.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through OpenCost.

  1. 04

    Get custom cost total

    Provides a total summary of third-party service expenses over a specific time window.

  2. 05

    Get allocation

    Queries the specific costs and resources assigned to Kubernetes workloads.

  3. 06

    Get custom cost timeseries

    Returns a time-based breakdown of costs for external services like Datadog or MongoDB Atlas.

Real work

What teams actually run

01

Namespace Cost Auditing

Ask your agent to find which namespaces exceeded their budget last week.

02

Cloud Bill Verification

Compare your OpenCost data against AWS or Azure billing exports to ensure accuracy.

03

External Service Monitoring

Track how much you are spending on Datadog or MongoDB Atlas in relation to your cluster spend.

04

Resource Efficiency Checks

Identify high-cost nodes or disks that are no longer being utilized effectively.

Automate a task

Put OpenCost 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

OpenCost 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.

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

You don't need a client to put OpenCost 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

1002ms average. Fast in production.

OpenCost is checked daily against the live service.

Daily averagePeak 1266ms
Oct 3Today
Fastest day
717ms
Slowest day
1266ms
14-day trend
Stable+3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 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 OpenCost, so you can see the experience inside your AI.

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

OpenCost Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_5JgTTx4dCCg1vy5LoQY7EOXCEeiHxNr943mMQtmk/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 — OpenCost capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "opencost-k8s-cost-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_5JgTTx4dCCg1vy5LoQY7EOXCEeiHxNr943mMQtmk/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 OpenCost in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work OpenCost owners hand off.

This MCP is built for technical teams managing large-scale Kubernetes environments who need to bridge the gap between infrastructure usage and cloud billing.

  • 01

    DevOps Engineers

    They use the agent to find expensive namespaces or identify orphaned resources.

  • 02

    FinOps Teams

    They use the agent to reconcile K8s allocations with actual cloud provider invoices.

  • 03

    Engineering Managers

    They use the agent to get quick cost summaries for specific projects or development cycles.

FAQ

Questions OpenCost owners ask.

  • 01

    How do I connect my existing OpenCost instance?

    You simply subscribe to the MCP on Vinkius and enter your OpenCost API Base URL. Once connected, your AI client can immediately start querying your data.

  • 02

    Which cloud providers are supported?

    The MCP can pull billing data from AWS, Azure, and GCP to help you reconcile K8s costs with your cloud provider bills.

  • 03

    Can I track costs for services outside of Kubernetes?

    Yes, you can use the custom cost capabilities to track and summarize expenses for third-party services like Datadog or MongoDB Atlas.

  • 04

    What kind of clients can I use this with?

    This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 05

    Can I see costs for specific pods or nodes?

    Yes, you can query cost allocations for pods, namespaces, controllers, and individual assets like nodes and disks.

  • 06

    Can I see costs grouped by a specific Kubernetes namespace?

    Yes. Use the get_allocation capability and set the aggregate parameter to 'namespace'. You can also specify a window like '7d' to see trends over the last week.

  • 07

    Does this server support viewing external cloud provider billing?

    Absolutely. The get_cloud_cost capability retrieves data directly from cloud provider billing reports (AWS CUR, Azure Export, GCP Billing) to give you a complete financial picture.

  • 08

    Can I track costs for non-Kubernetes services like Datadog?

    Yes, if configured in your OpenCost instance, you can use get_custom_cost_total or get_custom_cost_timeseries to query costs for third-party SaaS and infrastructure services.

Connect OpenCost to Claude, Cursor, ChatGPT & more