modelslab-v8
MCP serverAI & modelsModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.
Available today. Use it from your connected AI after setup.
Needs your own API account. Keys stay in your vault.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use modelslab-v8 to list models
Install modelslab-v8
The server’s own address, for the clients that take one directly. Or connect ahel once and every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user modelslab-v8 'https://modelslab.com/mcp/v8'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://modelslab.com/mcp/v8Add a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=modelslab-v8&config=eyJ1cmwiOiJodHRwczovL21vZGVsc2xhYi5jb20vbWNwL3Y4In0=Open the link and Cursor adds the server at that address.
ChatGPT
https://modelslab.com/mcp/v8In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add modelslab-v8 --url 'https://modelslab.com/mcp/v8'Run it once, then sign in with codex mcp login modelslab-v8 if the server asks for an account.
Tools it offers (8)
What this server listed when ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.
list-modelslist-providersendpoint-detailsimage-generationvideo-generationaudio-generation3d-generationfetch-generation
Advanced
- Delivery
- modelslab-v8 MCP server → your ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
io-github-modelslab-modelslab-v8- Source
- github.com/modelslab/modelslab-mcp
- Hosted endpoint
https://modelslab.com/mcp/v8
github.com/modelslab/modelslab-mcp