← Discover MCPs and Agents
a
MCPAI & MLMCP Registry

ai.kavel/kavel-mcp

Discover Kavel's AI photo/video generators, get tuned prompts, and open the right tool on kavel.ai.

Links

README

From the repo.

Kavel MCP

An MCP server for Kavel — bring Kavel's AI photo & video generators into any MCP client (Claude, Cursor, Cline, …). Ask for an effect, get a model-tuned prompt, and open the right tool to generate it on www.kavel.ai.

No account or API key required to use this server — it helps you pick a tool and craft a prompt, then hands off to Kavel's free-tier generators.

What it does

ToolWhat it returns
list_kavel_toolsBrowse/search Kavel's generators by goal (e.g. "make my dog look royal")
build_kavel_promptA model-tuned prompt recipe for a chosen effect, customized with your details
open_in_kavelThe direct generator URL, pre-set to the right mode
list_kavel_modelsThe image/video models Kavel runs and what each is good at

Featured generators

Install

Run directly with npx:

npx kavel-mcp

Claude Desktop / Claude Code

Add to your MCP config (claude_desktop_config.json or .mcp.json):

{
  "mcpServers": {
    "kavel": {
      "command": "npx",
      "args": ["-y", "kavel-mcp"]
    }
  }
}

Cursor / Cline

Point the client at the command npx -y kavel-mcp (stdio transport).

Skill (Claude Code / Cursor / Codex)

This repo also ships the kavel-image-studio agent skill (skills/kavel-image-studio/) — it helps pick the right Kavel generator, craft a model-tuned prompt, and hand off the generate link.

Install via the open agent-skills CLI:

npx skills add hanshs474/kavel-mcp

Or as a Claude Code plugin marketplace:

/plugin marketplace add hanshs474/kavel-mcp
/plugin install kavel-image-studio

Develop

npm install
npm run build
npm start

Links

License

MIT © Kavel

Gemini CLI

gemini extensions install https://github.com/hanshs474/kavel-mcp

Config for your environment

Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.

Tool

OS

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "{MCP_ENDPOINT_URL}"
    }
  }
}

Paste into mcpServers in the config file. Restart Cursor after saving.

If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.