Make your AI work with AI Model Usage Analytics
Connect your account once and let the AI you already use work with it, without building another integration or switching to a different AI. Pinpoint AI Model Costs and Usage Concentration in SaaS Products
4 live capabilities. One account. Your AI. Real work.
- Step 01
Connect
Link your account through Vinkius.
- Step 02
Authorize
You decide what your AI can access.
- Step 03
Pick your AI
Use it with the AI application you already use.
- Step 04
Get things done
Ask your AI to work with your connected account.
-
Works with
-
Waiting for input…
Why people use AI Model Usage Analytics
AI Model Usage Analytics : Pinpointing SaaS AI Cost Attribution
With this MCP, your agent handles the complexity. You ask for a cost breakdown, and it aggregates the data. You get a single, clean report showing the exact dollar cost for every feature, letting you stop guessing and start making precise, data-driven financial decisions.
What Vinkius changes
That you get a clear, actionable report showing exactly where your AI money is going and how you can spend less.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 7,300+ Connectors
- Real-world use case 01
The 'Black Box' Cost Problem
The CTO notices that AI costs are skyrocketing, but the engineering team can't tell if it's Feature A or Feature B.
- Real-world use case 02
Optimizing Model Selection
A PM wants to reduce monthly spend.
- Real-world use case 03
Killing Zombie Features
The team suspects an old feature is wasting money.
Complete set · 4capabilities
The complete AI Model Usage Analytics capability set.
These are the exact actions your AI can choose when you ask it to work with AI Model Usage Analytics.
01—04
4 capabilities in this set.
Part of 4 available through AI Model Usage Analytics.
- 01 Capability
Get feature cost breakdown
Calculates the precise dollar amount spent on every single product feature, giving you a clear financial picture.
- 02 Capability
Get routing efficiency score
Scores how well your system matches specific tasks to the most efficient AI model, preventing overspending on powerful models when a smaller one would suffice.
- 03 Capability
Identify optimization targets
Flags features that are expensive but see little user activity, or where the model choice is clearly wasteful.
- 04 Capability
Analyze usage concentration
Determines which few features are responsible for the majority of your AI model consumption, helping you focus your efforts.
Set up in minutes
One URL. Then ask AI Model Usage Analytics to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use AI Model Usage Analytics from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it AI Model Usage Analytics, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable AI Model Usage Analytics for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the AI Model Usage Analytics URL.
- Step 03
Save and start
Save the connection and enable AI Model Usage Analytics in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"ai-model-usage-analytics": {
"url": "https://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using AI Model Usage Analytics
Open Agent mode in chat and ask: "Using AI Model Usage Analytics, help me...". 4 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"ai-model-usage-analytics": {
"url": "https://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using AI Model Usage Analytics
Ask Copilot: "Using AI Model Usage Analytics, help me...". 4 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"ai-model-usage-analytics": {
"url": "https://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using AI Model Usage Analytics
Open Cascade and ask: "Using AI Model Usage Analytics, help me...". 4 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"ai-model-usage-analytics": {
"url": "https://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using AI Model Usage Analytics
Ask Cline: "Using AI Model Usage Analytics, help me...". 4 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add ai-model-usage-analytics --transport http "https://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using AI Model Usage Analytics
Ask Claude: "Using AI Model Usage Analytics, show me...". 4 tools are ready
Where the request belongs
Work AI Model Usage Analytics can move forward.
This MCP is essential for CTOs, Product Managers, and FinOps engineers running AI-powered SaaS. If you're tired of AI costs being a black box, this capability gives you the visibility to control your spending and prove ROI.
CTO / VP of Engineering
Uses the MCP to prove the ROI of new AI features and to justify infrastructure spending by showing precise cost attribution.
Product Manager
Uses the MCP to identify underperforming features that are draining resources, guiding the roadmap toward profitable areas.
FinOps Engineer
Uses the MCP to build cost models, pinpointing model inefficiencies and calculating potential savings from model switching.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsAI Feature Upsell Correlation
Quantify the impact of AI features on subscription upgrades.
AI SaaS Feature Churn Correlation
Quantify the impact of AI features on customer retention and calculate prevented churn revenue.
AI Feature Expansion Impact Analyzer
Quantify the financial and behavioral impact of AI features on SaaS expansion revenue and upsell conversion.
AI Feature Value Realization
Quantify the time to value and adoption efficiency of your AI features.
AI Feature Retention Analyzer
Quantify the impact of AI features on user retention and ROI.
AI Engagement Scoring
Analyze AI feature engagement, adoption rates, and churn risk.
Bring your own AI
Change the model, client or framework. Keep AI Model Usage Analytics 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 AI Model Usage Analytics.
The practical details behind the request, access and result.
How does AI Model Usage Analytics help me manage AI costs?
It gives you a clear, financial view of your AI spending. Instead of just seeing usage numbers, you see the dollar cost for every feature, letting you pinpoint exactly where your money is going.
Can I find out which feature is wasting the most money?
Yes. By running the optimization targets capability, you can identify features that are expensive but rarely used, giving you concrete areas to cut spending.
Is this better than just looking at my cloud bill?
Absolutely. Your cloud bill is raw data. This MCP analyzes that data, connecting usage patterns to specific product features and suggesting actionable fixes, which you can't do with a bill alone.
Does AI Model Usage Analytics help me with model selection?
Yes. It evaluates your model routing efficiency, telling you if you're using the right model for the job. This prevents overspending by ensuring you use the smallest, most capable model needed.
What if I launch a new feature? How do I predict its cost?
You can use the cost breakdown capability to model the expected cost increase before launch. This lets you bake cost management into your product roadmap, preventing budget surprises.
How does this capability help reduce AI costs?
By using identify_optimization_targets, you can find features where high costs don't match user engagement, allowing you to switch to more efficient models.
Can I see which features are using the most models?
Yes, the analyze_usage_concentration capability identifies which features are the primary drivers of AI model consumption.
How is routing efficiency measured?
The get_routing_efficiency_score capability compares the actual cost incurred by a feature against the theoretical minimum cost of using the most efficient model for that task.
One connection away
Give your agent a direct line to AI Model Usage Analytics.
Connect AI Model Usage Analytics once. Keep it beside 7,300+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available