kestra-io/mcp-server-python

Overview

A Python implementation of the Model Context Protocol (MCP) server for Kestra. It enables Kestra's AI agents to call Python-based tools and scripts as part of their workflows. The server exposes MCP endpoints that Kestra can invoke to execute custom Python logic.

Best for

Best for
Developers building custom Python tools for Kestra AI agents

Use cases

• Integrating Python scripts into Kestra AI agent workflows
• Exposing custom Python functions as tools for AI agents
• Building MCP-compatible tool servers for Kestra orchestration

How to use

Install

uv pip install -r requirements.txt

Tested with

Claude Desktop, Cursor, Windsurf, Continue, VS Code

Example client config

{\n  "mcpServers": {\n    "kestra": {\n      "command": "docker",\n      "args": [\n        "run",\n        "-i",\n        "--rm",\n        "--pull",\n        "always",\n        "-e",\n        "KESTRA_BASE_URL",\n        "-e",\n        "KESTRA_TENANT_ID",\n        "-e",\n        "KESTRA_MCP_DISABLED_TOOLS",\n        "-e",\n        "KESTRA_MCP_LOG_LEVEL",\n        "-e",\n        "KESTRA_USERNAME",\n        "-e",\n        "KESTRA_PASSWORD",\n        "ghcr.io/kestra-io/mcp-server-python:latest"\n      ],\n      "env": {\n        "KESTRA_BASE_URL": "http://host.docker.internal:8080/api/v1",\n        "KESTRA_TENANT_ID": "main",\n        "KESTRA_MCP_DISABLED_TOOLS": "ee",\n        "KESTRA_MCP_LOG_LEVEL": "ERROR",\n        "KESTRA_USERNAME": "admin@kestra.io",\n        "KESTRA_PASSWORD": "your_password"\n      }\n    }\n  }\n}

Notes

A Python implementation of the Model Context Protocol (MCP) server for Kestra. It enables Kestra’s AI agents to call Python-based tools and scripts as part of their workflows. The server exposes MCP endpoints that Kestra can invoke to execute custom Python logic.

27 stars on GitHub. Last updated 2026-05-04. Licensed Apache-2.0.

Use cases

• Integrating Python scripts into Kestra AI agent workflows
• Exposing custom Python functions as tools for AI agents
• Building MCP-compatible tool servers for Kestra orchestration

Pros

• Lightweight and Python-native, easy to extend with existing Python code
• Open source with permissive licensing (vendor: Various)
• Directly integrates with Kestra’s AI agent framework

Cons

• Low GitHub stars (27) indicate limited community adoption and testing
• Documentation and stability may be sparse for production use
• Tied to the Kestra ecosystem, not a general-purpose MCP server

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.