Kestra
Live Kestra-Plugin-Schemas, Blueprints und Dokumentationen für KI-Agenten, die Kestra-Workflows erstellen
Gehosteter MCP-Server
npx add-mcp 'https://api.kestra.io/v1/mcp'Installiert in Claude Code, Codex, Cursor und mehr
Dokumentation
Documentation Menu
Version·2.0 Latest (2.0) 1.3 1.2 1.1 1.0
Search
Ctrl + K
Connect Your Coding Agent to Kestra Docs and Plugin Schemas
Copy Page
- Copy as Markdown
- View as Markdown
- Open in ChatGPT
- Open in Claude
- Edit This Page
Table of Contents
Table of Contents
Get Involved
For the complete documentation index, see llms.txt. For a full content snapshot, see llms-full.txt. Append
.mdto anykestra.io/docs/*URL for plain Markdown.
Give your coding agent live access to Kestra plugin schemas, blueprints, and documentation through a hosted MCP server.
This page is for developers who write flows in Claude Code, Cursor, Codex, or another coding agent. The server is public, read-only, and hosted by Kestra; it doesn’t connect to your Kestra instance. To let external AI agents run your flows as tools, see Flow MCP servers.
What the server provides
The Docs MCP server implements the Model Context Protocol, a standard that lets AI tools query external data sources at runtime. Once connected, your agent can look up:
- Plugin reference: task schemas, properties, inputs, outputs, and version history for every Kestra plugin
- Blueprints: ready-to-use flow templates for common integration patterns
- Documentation: searchable product docs, including concepts, how-to guides, and reference pages
With the server connected, the agent checks current plugin properties instead of guessing them from training data.
Connect the MCP server
The server URL is:
https://api.kestra.io/v1/mcp
Claude Code
Add the server with the Claude Code CLI:
claude mcp add kestra --transport http https://api.kestra.io/v1/mcp
Or add it directly to ~/.claude.json:
{ "mcpServers": { "kestra": { "type": "http", "url": "https://api.kestra.io/v1/mcp" } }}
Cursor
Add the following to your Cursor MCP configuration (.cursor/mcp.json in your project or ~/.cursor/mcp.json globally):
{ "mcpServers": { "kestra": { "url": "https://api.kestra.io/v1/mcp" } }}
Other AI tools
Any MCP-compatible tool can connect using the HTTP transport and the URL above. Refer to your tool’s documentation for the exact configuration format.
Available tools
Once connected, the server exposes these tools to your agent:
| Category | Tools |
|---|---|
| Plugins | List plugins, browse tasks by plugin, retrieve task schemas, check plugin versions |
| Blueprints | Search and browse blueprints, retrieve full blueprint flow YAML |
| Docs | Search documentation, retrieve pages, navigate doc hierarchy |
| Reference | List task runners, triggers, secret managers, storage backends, log exporters |
Example usage
Plugin schema lookup
Ask your agent about a specific task’s properties:
“What properties does the
io.kestra.plugin.jdbc.postgresql.Querytask accept?”
The agent retrieves the live task schema and returns a summary similar to this:
io.kestra.plugin.jdbc.postgresql.Query — key properties:- url (string, required): JDBC connection string, e.g. jdbc:postgresql://host:5432/db- username (string, required)- password (string, required): use {{ secret('KEY') }} to avoid storing credentials in plain text- sql (string, required): the SQL query to execute- fetchType (enum): FETCH, FETCH_ONE, STORE, or NONE — controls how results are returned- fetchSize (integer): rows per fetch batch, default 1000
Blueprint retrieval
Ask your agent to find a blueprint by use case:
“Find a blueprint for triggering a flow when a file lands in S3.”
The agent searches the blueprints library and returns matching flow YAML. The excerpt below shows the shape of a result; the full blueprint includes every task property:
id: s3_triggernamespace: company.teamtasks: - id: process type: io.kestra.plugin.scripts.python.Script # ...triggers: - id: watch type: io.kestra.plugin.aws.s3.Trigger bucket: your-bucket prefix: incoming/ interval: PT1M
Documentation lookup
For prose questions, such as “What does the whenMissingInSource property do in NamespaceSync?”, the agent retrieves and summarizes the relevant docs page.
Next steps
- Agent Skills: teach your coding agent how to write, harden, and deploy flows. Skills and this server work together.
kestractl: let the agent validate and deploy flows to your instance.- Docs for Agents: every other machine-readable Kestra resource, such as
llms.txt, Markdown docs, and OpenAPI specs.
Previous Agent SkillsAgent Skills for Kestra: Teach Coding Agents to Write FlowsNext
Was this page helpful?
Yes No
Send Feedback
😔
Share your thoughts (Optional)
Cancel Submit
Ask AI
A
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://kestra.io/"},{"@type":"ListItem","position":2,"name":"Docs","item":"https://kestra.io/docs"},{"@type":"ListItem","position":3,"name":"Develop with ai","item":"https://kestra.io/docs/develop-with-ai"},{"@type":"ListItem","position":4,"name":"Kestra Docs MCP Server for AI Coding Agents","item":"https://kestra.io/docs/develop-with-ai/kestra-mcp-resources"}]}
{"@context":"https://schema.org","@type":"Organization","@id":"https://kestra.io/#organization","name":"Kestra Technologies","url":"https://kestra.io","logo":"https://kestra.io/logo.svg","description":"Kestra is the open-source orchestration platform for data, AI, and infrastructure workflows. Event-driven, language-agnostic, and built for enterprise scale.","foundingDate":"2021","sameAs":["https://github.com/kestra-io/kestra","https://www.linkedin.com/company/kestra","https://x.com/kestra_io","https://hub.docker.com/r/kestra/kestra"],"contactPoint":{"@type":"ContactPoint","contactType":"sales","url":"https://kestra.io/demo"}}
{"@context":"https://schema.org","@type":"TechArticle","@id":"https://kestra.io/docs/develop-with-ai/kestra-mcp-resources","headline":"Docs MCP Server","url":"https://kestra.io/docs/develop-with-ai/kestra-mcp-resources","inLanguage":"en","description":"Connect Claude Code, Cursor, or another coding agent to the hosted Kestra MCP server for live plugin schemas, blueprints, and docs while you write flows.","isPartOf":{"@type":"WebSite","@id":"https://kestra.io/#website"},"about":{"@type":"SoftwareApplication","@id":"https://kestra.io/#software"},"author":{"@id":"https://kestra.io/#organization"},"publisher":{"@id":"https://kestra.io/#organization"}}