How to Use the CometAPI MCP in Claude

Q: How do I install the CometAPI tools inside Claude Desktop?

Open your local claudedesktopconfig.json file and add the server setup under your mcpServers key. Once you restart the desktop app, the hammer icon will display your new tools like transcribeaudiototext.

Q: Why is Claude Desktop failing to run my image generations through CometAPI?

Check your connection status first. Run checkapihealth to verify if the external endpoints are active before triggering generateaiimage.

Q: Which AI models can I call through this integration?

Your agent queries listsupportedaiproviders to find available backends. From there, you can run completions on any supported LLM.

Run multi-provider AI generations and audio transcriptions directly inside your Claude Desktop app with CometAPI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CometAPI MCP to Claude Desktop

Create your Vinkius account to connect CometAPI to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CometAPI with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate assets directly in Claude Desktop

Let Claude Desktop build assets for you on the fly using this MCP setup. When you write a prompt, your agent uses `generate_ai_image` to spin up visuals or `convert_text_to_speech` to create voiceovers without leaving your chat window. You get the files saved locally via the desktop app's native file access. It bypasses the need to jump between midjourney tabs or browser-based voice generators.

Compare model outputs using this MCP Server

Stop guessing which model handles your prompt best. This MCP Server lets your agent invoke `create_ai_chat_completion` across different providers like Gemini or GPT-4, returning results side-by-side inside Claude Desktop. Your agent calls `list_available_ai_models` to see what is currently supported. This makes testing prompts across different engines fast and keeps your workflow inside a single chat window.

Track API costs and usage in real-time

Running multiple API keys gets expensive fast. By executing `get_api_usage_statistics` directly in Claude Desktop, your agent checks your current spend before you run another heavy batch of image or audio jobs. You can ask your agent to pull model costs via `get_pricing_information` to find the cheapest model for your task. This keeps your development budget under control without leaving your workspace.

Setup guide

Set up CometAPI MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The CometAPI MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the CometAPI MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under cometapi-mcp.

json

{
  "mcpServers": {
    "cometapi-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CometAPI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CometAPI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CometAPI MCP in Claude Desktop

Open your local `claude_desktop_config.json` file and add the server setup under your mcpServers key. Once you restart the desktop app, the hammer icon will display your new tools like `transcribe_audio_to_text`.

Yes, you can paste the remote MCP server URL into your Claude.ai integration settings. This lets your web agent run `create_ai_chat_completion` without needing a local installation on your machine.

Check your connection status first. Run `check_api_health` to verify if the external endpoints are active before triggering `generate_ai_image`.

Your agent queries `list_supported_ai_providers` to find available backends. From there, you can run completions on any supported LLM.

Your voice recordings, text prompts, and generated speech files pass through a secure Vinkius sandbox. Nothing is stored permanently on our servers, keeping your raw media files completely private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript