# Veqen: AI cost monitoring and protection

> Veqen: AI cost monitoring and protection is a freemium MCP server for finance and payments. Tracks AI spend per person and customer, flags unexplained key use, checks bills. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $10 a month
- **Platforms:** Web, API
- **Website:** https://veqen-app.com
- **MCP Registry name:** io.github.Keyveve/veqen
- **Categories:** [finance and payments](https://ai-powered.com/categories/finance-and-payments), [analytics and data](https://ai-powered.com/categories/analytics-and-data), [security](https://ai-powered.com/categories/security)
- **Listing updated:** 2026-11-16

## About

Veqen matches every AI charge to the person, customer or project that made it, key by key and hour by hour, and flags what nobody made. It covers work and coding agents such as ChatGPT, Claude, Copilot, Claude Code, Cursor, Codex and Devin, plus model APIs for companies building on AI.

The pitch is what no single provider shows: one bill per person across all agents, a stolen or misused key shut off while leaving others alone, and each day's charge repriced at the provider's own rate card with a claim for any difference. For finance it produces chargeback to cost centres and journal entries for QuickBooks or Xero. Setup uses read-only keys; the site says it keeps token counts, models, prices and tags but never prompts, code or responses, and it is not a proxy, so requests go straight to the provider.

An optional SDK for Python and TypeScript, or OpenTelemetry export, names the customer or feature behind each call. A free audit reports the last 30 days of unexplained spend, overcharges, keys held by departed staff and idle seats.

## Features

- **Per-person billing:** One bill per person and team across connected agents.
- **Key protection:** Matches key usage to what the team made and shuts off only that key.
- **Invoice checks:** Reprices daily charges against provider rate cards and claims differences.
- **Month-end close:** Chargeback and journal entries for QuickBooks or Xero.
- **Customer margin:** SDK tags give cost and margin per customer and feature.
- **No proxy:** Requests go direct to the provider, and prompts are not kept.

## Good for

- Find who spent an unexplained AI charge
- Catch a stolen API key early
- Claim overcharges back from a provider
- Close the month with AI costs charged to cost centres
- Work out margin per customer

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http veqen https://veqen-app.com/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://veqen-app.com/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "veqen": {
      "url": "https://veqen-app.com/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "veqen": {
      "type": "http",
      "url": "https://veqen-app.com/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "veqen": {
      "serverUrl": "https://veqen-app.com/mcp"
    }
  }
}
```

### Grok Bot (Grok Bot desktop app → Connect apps → Add a custom connector)

```sh
https://veqen-app.com/mcp
```

Enter a Name (for example "Veqen: AI cost monitoring and protection"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "veqen": {
      "type": "http",
      "url": "https://veqen-app.com/mcp"
    }
  }
}
```

## FAQ

### Does Veqen see my prompts?

The site says it keeps token counts, models, prices and tags, never prompts, code or responses.

### Does it sit in the request path?

No. It is not a proxy, so nothing breaks if Veqen is down.

### Is there a free option?

Yes: a free audit at any size, and a Free plan for up to 3 people on the agents product.

### What do paid plans cost?

Agents Team is $10 per active person a month; product inference starts at $39 a month for up to $5,000 of watched spend.

### Is Veqen: AI cost monitoring and protection free?

Veqen: AI cost monitoring and protection has a free plan, with paid plans for more usage or features. Paid plans start at $10 a month.

### How do I add Veqen: AI cost monitoring and protection to Claude Code?

Run this command in your terminal: claude mcp add --transport http veqen https://veqen-app.com/mcp

### What are the best alternatives to Veqen: AI cost monitoring and protection?

The closest alternatives to Veqen: AI cost monitoring and protection are Veqen Pricing: AI model costs, CloudQuell, VouchSafe, Screwtape.ai and TraxAgent.

## Where this comes from

- Description: written from the project's website.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Veqen Pricing: AI model costs](https://ai-powered.com/mcp/veqen-pricing-ai-model-costs): Veqen Pricing: AI model costs is a free MCP server for ai models and llm tooling.
- [CloudQuell](https://ai-powered.com/mcp/cloudquell): CloudQuell is a freemium MCP server for cloud and infrastructure.
- [VouchSafe](https://ai-powered.com/mcp/vouchsafe): VouchSafe is a freemium MCP server for security.
- [Screwtape.ai](https://ai-powered.com/mcp/screwtape-ai): Screwtape.ai is a freemium MCP server for finance and payments.
- [TraxAgent](https://ai-powered.com/mcp/traxagent): TraxAgent is a freemium MCP server for finance and payments.
- [Qovia](https://ai-powered.com/mcp/qovia): Qovia is a paid MCP server for analytics and data.
- [OpenProfit](https://ai-powered.com/mcp/openprofit): OpenProfit is an open-source MCP server for finance and payments.
- [sebbi.pro - the proof layer for AI](https://ai-powered.com/mcp/sebbi-pro-the-proof-layer-for-ai): sebbi.pro - the proof layer for AI is an MCP server for finance and payments.

---
Source: https://ai-powered.com/mcp/veqen-ai-cost-monitoring-and-protection
