Compatible with every major AI agent and IDE
What is the OpenCost (K8s Cost) MCP Server?
Connect your OpenCost instance to any AI agent to gain real-time visibility into your Kubernetes spending and infrastructure efficiency through natural language.
What you can do
- Workload Allocation — Query costs and resources allocated to clusters, nodes, namespaces, controllers, and pods using
get_allocation. - Asset Inspection — Retrieve backing cost data for physical infrastructure like Nodes, Disks, and Load Balancers via
get_assets. - Cloud Billing Integration — Access AWS CUR, Azure Export, and GCP Billing data directly with
get_cloud_costto reconcile K8s costs with provider bills. - Third-Party Costs — Track external service expenses (e.g., Datadog, MongoDB Atlas) using custom cost timeseries and total summary tools.
- Granular Filtering — Aggregate data by labels, annotations, or service levels to understand exactly where your budget is going.
How it works
- Subscribe to this server
- Enter your OpenCost API Base URL
- Start auditing your cloud spend from Claude, Cursor, or any MCP client
Who is this for?
- DevOps & Platform Engineers — Identify expensive namespaces or orphaned resources without manual dashboard diving.
- FinOps Teams — Reconcile internal Kubernetes allocations with external cloud provider billing reports instantly.
- Engineering Managers — Get quick summaries of project-based costs to stay within budget during development cycles.
Built-in capabilities (6)
Query costs and resources allocated to Kubernetes workloads
Retrieve backing cost data broken down by individual assets
Retrieve cloud cost data directly from cloud provider billing reports
g., Datadog, MongoDB Atlas). Get samples of third-party service costs over time steps
Get summary of third-party costs over a window
Change OpenCost log level at runtime
Why Cursor?
Cursor's Agent mode turns OpenCost (K8s Cost) into an in-editor superpower. Ask Cursor to generate code using live data from OpenCost (K8s Cost) and it fetches, processes, and writes. all in a single agentic loop. 6 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
OpenCost (K8s Cost) in Cursor
OpenCost (K8s Cost) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect OpenCost (K8s Cost) to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for OpenCost (K8s Cost) in Cursor
The OpenCost (K8s Cost) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
OpenCost (K8s Cost) for Cursor
Every tool call from Cursor to the OpenCost (K8s Cost) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see costs grouped by a specific Kubernetes namespace?
Yes. Use the get_allocation tool and set the aggregate parameter to 'namespace'. You can also specify a window like '7d' to see trends over the last week.
Does this server support viewing external cloud provider billing?
Absolutely. The get_cloud_cost tool retrieves data directly from cloud provider billing reports (AWS CUR, Azure Export, GCP Billing) to give you a complete financial picture.
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.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Freshservice
12 toolsManage your IT service desk, track tickets, and oversee assets via AI agents with Freshservice.

Woodpecker CI
34 toolsManage your Woodpecker CI instance — control pipelines, monitor agents, and configure repositories directly from your AI agent.

Roblox Social & Group Intelligence
9 toolsThe definitive server for the Roblox social graph — track user profiles, friend lists, and group rankings via AI.

Hugging Face
15 toolsAccess thousands of pre-trained AI models for NLP, vision, and audio tasks with the largest open-source machine learning hub.
