kestra

Give your AI coding agent live, up-to-date knowledge of Kestra, the open-source orchestration platform.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Search: Search Kestra plugins, docs, blueprints, or blogs. Returns matching results with highlights. Parameter 'query' is the search text. Optional 'type' must be one of: PLUGINS (default), DOCS, BLUE
  • Task Schema: Get the full schema/documentation for a specific Kestra task class. Returns properties schema, outputs schema and documentation. Parameter 'cls' is the full class name like 'io.kestra.plu
  • List Plugins: List available Kestra plugins with summary info (name, title, group, description, categories, and counts per element type: taskCount, triggerCount, taskRunnerCount, storageCount, secretM

What data it sees

Do you need an account

No: the server works without sign-in

Give your AI coding agent live, up-to-date knowledge of Kestra, the open-source orchestration platform. Instead of guessing YAML syntax from training data, your agent queries the real reference:

  • Plugins: task schemas, properties, outputs and version history for 2,000+ Kestra plugins
  • Blueprints: search and retrieve ready-to-use flow templates for data, infrastructure and AI use cases
  • Documentation: search and read Kestra docs pages, from concepts to how-to guides
  • Reference: list available task runners, triggers, secret managers, storage backends and log exporters

Public server, no authentication or API key required. Works with Claude Code, Cursor, VS Code and any MCP client.

Docs: https://kestra.io/docs/ai-tools/kestra-mcp-resources

How to connect

How to connect kestra to Claude

The server address to paste into Claude settings:

https://kestra--kestra.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect kestra to ChatGPT

The server address to paste into ChatGPT settings:

https://kestra--kestra.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect kestra to Cursor

The server address to paste into Cursor settings:

https://kestra--kestra.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (12)

Raw names from tools/list. Only developers need these.

searchSearch Kestra plugins, docs, blueprints, or blogs. Returns matching results with highlights. Parameter 'query' is the search text. Optional 'type' must be one of: PLUGINS (default), DOCS, BLUEPRINTS, BLOGS.
task_schemaGet the full schema/documentation for a specific Kestra task class. Returns properties schema, outputs schema and documentation. Parameter 'cls' is the full class name like 'io.kestra.plugin.core.log.Log'. Optional 'properties' must be one of: 'declared' (default, only properties declared by the task) or 'all' (also includes inherited properties).
list_pluginsList available Kestra plugins with summary info (name, title, group, description, categories, and counts per element type: taskCount, triggerCount, taskRunnerCount, storageCount, secretManagerCount, logExporterCount). Use this to discover what plugins exist. Filter by count > 0 to find plugins with a specific element type. Optional 'category' parameter filters by: AI, BUSINESS, CLOUD, CORE, DATA, INFRASTRUCTURE. Optional 'detail' parameter: 'full' (default) includes plugin descriptions, 'concise' omits them to save tokens.
plugin_tasksList all tasks and triggers for a specific Kestra plugin, grouped by subpackage. The 'plugin' parameter accepts a plugin name like 'plugin-aws' or 'core', or a group like 'io.kestra.plugin.aws'.
list_installed_versionsList the currently installed version of each Kestra plugin. Shows each plugin's name, group, and version number. Optional 'plugin' parameter filters by plugin name (e.g. 'aws', 'gcp'). For the full GitHub release history of a plugin, use plugin_release_history instead.
list_plugin_elementsList all elements of one type across all Kestra plugins. 'elementType' must be one of: TASK_RUNNER (task runner backends, e.g. Kubernetes, GCP Batch, AWS Batch, Docker), TRIGGER (trigger types, e.g. Schedule, Webhook, Realtime variants, JDBC and message queue triggers), STORAGE (internal storage backends Kestra uses for internal state and outputs, e.g. GCS, S3, Azure Blob Storage, MinIO), SECRET_MANAGER (secret manager backends, e.g. HashiCorp Vault, AWS Secrets Manager, GCP Secret Manager, Azure Key Vault, 1Password, CyberArk, Doppler), LOG_EXPORTER (log shipper backends to ship execution logs to external systems), APP (Kestra App plugins), APP_BLOCK (building blocks used inside Apps), CHART (dashboard chart types), DATA_FILTER (dashboard data filters), DATA_FILTER_KPI (dashboard KPI data filters), ADDITIONAL_PLUGIN (miscellaneous plugin classes not covered by another element type). Each entry includes FQCN, title, description, and the owning plugin name/group. Always call this tool when asked what backends of a given type are available -- do NOT guess plugin names. Optional 'detail' parameter: 'full' (default) includes element descriptions, 'concise' omits them to save tokens.
plugin_release_historyGet the full release history of a Kestra plugin from GitHub, including which Kestra version each release targets. Parameter 'plugin' is the repo name: plugins are 'plugin-aws', 'plugin-gcp', while storage backends, secret managers and log data stores have their own repositories, e.g. 'storage-gcs', 'secret-vault', 'log-data-store-splunk'. A bare name is prefixed with 'plugin-'. Optional 'limit' sets max releases to return (default: 10, max: 20). For the currently installed version of each plugin, use list_installed_versions instead.
search_docsSearch Kestra documentation pages by keyword. Returns matching pages with their parsedUrl and title. Optional parameter 'version' targets a specific Kestra version (e.g. 'v0.23'); defaults to the current installed version.
get_docFetch the full markdown content and metadata for a Kestra documentation page. Pass either the parsedUrl path (e.g. 'docs/getting-started') from search_docs, or a docId. If the identifier contains a '/' it is treated as a path first; otherwise a docId lookup is attempted. Optional parameter 'version' targets a specific Kestra version (e.g. 'v0.23'); defaults to the current installed version.
list_doc_childrenList all documentation pages under a given path prefix, ordered by their navigation order. Returns each child's parsedUrl and metadata. Parameter 'path' is the parent path prefix (e.g. 'docs/getting-started'). Optional parameter 'version' targets a specific Kestra version (e.g. 'v0.23'); defaults to the current installed version.
search_blueprintsSearch Kestra flow blueprints -- ready-made flow templates. Returns matching blueprints with id, title, description, tags, includedTasks (FQCNs), and ee (Enterprise Edition flag). Optional parameters: 'query' (search text), 'tags' (comma-separated), 'types' (comma-separated FQCNs to filter by includedTasks -- use list_plugin_elements to get valid FQCNs), 'page' (default: 1), 'size' (results per page, default: 10).
get_blueprint_flowGet the full YAML flow definition for a specific Kestra blueprint. Parameter 'id' is the blueprint ID from the search_blueprints tool.