Skip to main content
Krea exposes a hosted Model Context Protocol (MCP) server for agents and coding assistants. Use it when you want an MCP-compatible client to call Krea directly instead of writing API requests by hand.
MCP usage uses the same API token and API balance as direct API calls. See API Keys & Billing before connecting a client.

​
Server Details

SettingValue
TransportStreamable HTTP
URLhttps://api.krea.ai/mcp
Header keyAuthorization
Header valueBearer KREA_API_TOKEN
Replace KREA_API_TOKEN with a token from krea.ai/app/api/tokens. Only workspace owners and admins can create API tokens.
Store MCP credentials the same way you store API keys. Do not commit MCP configuration files that contain real tokens.

​
Claude Code

Run this command in your terminal: 
claude mcp add --transport http krea-ai \
  https://api.krea.ai/mcp \
  --header "Authorization: Bearer KREA_API_TOKEN"
Restart Claude Code or reload your MCP servers after adding the server.

​
Codex

  1. Open Settings > MCP servers in Codex.
  2. Add a new server.
  3. Select Streamable HTTP as the transport.
  4. Paste the server URL:
https://api.krea.ai/mcp
  1. Add this header:
Authorization: Bearer KREA_API_TOKEN

​
Cursor

Open the command palette, search for Open MCP settings, then add this entry to mcp.json: 
{
  "mcpServers": {
    "krea-ai": {
      "url": "https://api.krea.ai/mcp",
      "headers": {
        "Authorization": "Bearer KREA_API_TOKEN"
      }
    }
  }
}
Restart Cursor after saving the file.

​
Using Krea Through MCP

Once connected, ask your agent to list Krea models or inspect a model schema before generating. Model IDs match the API paths used in the rest of the developer docs, such as image/krea/krea-2/medium or video/google/veo-3.1. For example: 
List the available Krea image models, then generate an image with Krea 2 using a 16:9 aspect ratio.
If a model is deprecated, Krea returns deprecation metadata through MCP model discovery. See Deprecations for migration guidance.

​
Troubleshooting

IssueFix
Authentication failsConfirm the header is exactly Authorization: Bearer KREA_API_TOKEN and that the token has not been revoked.
Client cannot connectConfirm the client is configured for Streamable HTTP and uses https://api.krea.ai/mcp.
Generation is rejected with 402Add API balance at krea.ai/app/api.
Model call failsAsk your agent to inspect the model schema before retrying. MCP requests use the same model inputs as the API.

​
Next Steps

API Keys & Billing

Create API tokens and manage API balance.

Interactive Playground

Try requests in the Krea app before asking an agent to run them.

Deprecations

See how MCP exposes model migration metadata.

Model APIs

Browse endpoint schemas and model parameters.