技能潮 SkillTide 提交收录
官方说明3 个来源MCP 服务3 天前
kestra-io/mcp-server-python

kestra-io/mcp-server-python

Python MCP for Kestra AI Agents
在 GitHub 查看 ↗直链 · 无中转页
来源明细
收录自 abordage/awesome-mcp 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
收录与活跃
收录于 2026-10-14 · 最近见到 2026-10-16 · 共见到 4 次 · 被 3 个来源列出
评分构成
综合分 303 · 3 个来源 · mcp
常见问题(答案都来自我们的记录)
怎么安装?
我们【没有】从该仓库取到安装命令(我们的 install 覆盖率只有约 4%)。请看它的 README 或 releases 页。
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
我们收录于 2026-10-14;最近见到 2026-10-16。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
第三方质量标记

Kestra Python MCP Server

以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →

You can run the MCP Server in a Docker container. This is useful if you want to avoid managing Python environments or dependencies on your local machine.
Using Kestra AI Agent
See kestra_mcp_docker.
Minimal configuration for OSS users
Paste the following configuration into your MCP settings (e.g., Cursor, Claude, or VS Code):
Minimal configuration for EE users
Detailed Configuration using Docker
**Notes:**
- Replace , , and with your actual credentials.
- For OSS installations, you can use KESTRA_USERNAME and KESTRA_PASSWORD instead of KESTRA_API_TOKEN.
- To disable Enterprise Edition tools in OSS, set KESTRA_MCP_DISABLED_TOOLS=ee.
- The host.docker.internal hostname allows the Docker container to access services running on your host machine (such as the Kestra API server on port 8080). This works on macOS and Windows. On Linux, you may need to use the host network mode or set up a custom bridge.
- The -e flags pass environment variables from your MCP configuration into the Docker container.
---
Kestra version support
Both Kestra 1.x and Kestra 2.x are supported by the same image, and nothing has to be configured for either.
Several endpoints were changed in Kestra 2.0. The execution actions were moved under /actions/, the per-endpoint search parameters were replaced by the unified filters[field][OPERATION] model, backfill creation was moved to /triggers/backfill/create, and KV listing was moved to GET /kv. A 1.x query parameter sent to a 2.x server is ignored rather than rejected, so a request can appear to succeed while the results come back unfiltered.
The server version is read once from GET /api/v1/configs on the first tool call and every request is then built for that major. Where that endpoint is unreachable, behind a proxy that does not forward it for instance, the major can be set explicitly:
Two differences between the majors remain visible in the tool output:
- **Dashboards** - from 2.0 on, dashboards can only be created over the API in the Enterprise Edition, so generate_dashboard with auto_create returns the generated YAML together with a warning on OSS 2.x.
- **Namespace file moves** - on Kestra 2.x, a file written to a path that was previously moved away is stored under a versioned name, and a later move of that path fails with a 500. The error is reported with the suggestion to delete and re-upload instead.
---
Available Tools
- 🔄 backfill
- ⚙️ ee (Enterprise Edition tools)
- ▶️ execution
- 📁 files
- 🔀 flow
- 🗝️ kv
- 📋 logs
- 🌐 namespace
- 🔁 replay
- ♻️ restart
- ⏸️ resume
**Note:** The ee tool group contains Enterprise Edition specific functionality and is only available in EE/Cloud editions. For OSS users, you can disable EE tools by adding KESTRA_MCP_DISABLED_TOOLS=ee to your .env file.
Optionally, you can include KESTRA_MCP_DISABLED_TOOLS in your .env file listing the tools that you prefer to disable. For example, if you want to disable Namespace Files tools, add this to your .env file:
To disable multiple tools, separate them with comma:
Logging Configuration
By default, the MCP server only logs ERROR level messages to minimize noise. You can control the logging level using the KESTRA_MCP_LOG_LEVEL environment variable:
来源
awesome · https://github.com/kestra-io/mcp-server-python
按领域浏览
MCP 服务
收录于
昨天

更多MCP 服务

查看MCP 服务全部 5,525 条 →

所属领域与标签

每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。

浏览全部领域 →

← 返回索引