Schema | Kestra Python MCP Server

Kestra Python MCP Server

Official

Describes the environment variables required to run the server.

Name	Required	Description	Default
`GOOGLE_API_KEY`	No	Your Google API key for Gemini models
`KESTRA_BASE_URL`	No	The base URL for the Kestra API	http://host.docker.internal:8080/api/v1
`KESTRA_PASSWORD`	No	Password for basic authentication
`KESTRA_USERNAME`	No	Username for basic authentication
`HELICONE_API_KEY`	No	Optional Helicone API key for codegen tracing
`KESTRA_API_TOKEN`	No	Your Kestra API token (for EE/Cloud users)
`KESTRA_TENANT_ID`	No	The Kestra tenant ID	main
`GOOGLE_GEMINI_MODEL_AGENT`	No	Google Gemini model to use for agent functionality	gemini-2.0-flash
`KESTRA_MCP_DISABLED_TOOLS`	No	Comma-separated list of tools to disable (e.g., 'ee,codegen')
`GOOGLE_GEMINI_MODEL_CODEGEN`	No	Google Gemini model to use for code generation	gemini-2.5-flash

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kestra-io/mcp-server-python'

If you have feedback or need assistance with the MCP directory API, please join our Discord server