Connect Your Coding Agent to Kestra Docs and Plugin Schemas

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:

Example usage

Plugin schema lookup

Ask your agent about a specific task’s properties:

“What properties does the io.kestra.plugin.jdbc.postgresql.Query task 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_trigger
namespace: company.team

tasks:
  - 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.