dltHub AI Workbench

dlt (data load tool) is an open-source Python library for loading data from APIs and databases into a warehouse or lakehouse. dltHub (paid platform) extends dlt with enterprise-grade features tailored to the needs of coding agents: transformations, data quality validation, managed runtime infrastructure, managed data apps, and an AI-powered workspace environment.

The dltHub AI Workbench is a collection of toolkits that give AI coding assistants step-by-step workflows to build data pipelines with dlt. You can use the workbench as-is or fork and customize it for your own stack. The dlt ai CLI installs toolkit components into the right locations for your assistant and runs the workspace MCP server.

Build toolkits cover ingestion (REST API, SQL), transformation, and data quality; Run toolkits handle deployment and exploration. The REST API toolkit is backed by the dltHub context — over 9,700 source definitions the agent queries to find verified connectors before writing code.

The dltHub AI Workbench is tested with Claude Code, Cursor, and Codex and may work with other AI coding assistants. We recommend workings in accept edits (Claude) / --approval-mode (Codex) mode to review the changes and familiarizing with dlthub AI workflows when getting started with the dlthub AI workbench.

The dlthub AI workbench supports the iterative data engineering workflow

Building data pipelines is iterative and covers two major phases — ingestion and transformations — each following the same inner loop:

Build (local development)

• Develop the pipeline iteratively — for ingestion: first REST API endpoint, then additional endpoints; for transformation: data model first, then the full transformation pipeline
• Explore the loaded data and validate it after each step
• Loop back to refine until the pipeline is solid

Run (production)

• Deploy the ingestion or transformation pipeline to production
• Serve insights via data apps built on top of the loaded data

The outer loop connects the two phases: insights from the transformation and serving layer feed back into ingestion refinement. The workbench Build toolkits support the local development loop; the Run toolkits handle deployment and data apps.

dltHub AI Workbench Toolkits

The workbench gives your coding assistant toolkits — that contain a structured, guided workflow for a specific phase. Instead of generating ad-hoc code, the assistant follows a defined sequence of steps from start to finish.

A Toolkit contains skills, commands, rules, and an MCP server — tied together by a workflow that tells the assistant which skill to run at each step and how to leverage the MCP.

All toolkits depend on init for shared rules, secrets handling, and the MCP server. When using the dlt ai CLI, init is installed automatically as a dependency. When using the Claude marketplace, install the init plugin separately.

Toolkit components

Component	What it is	When it runs
Skill	Step-by-step procedure the assistant follows	Triggered by user intent or explicitly with /skill-name
Command	A slash command for a specific action	User invokes with /toolkit:command
Rule	Always-on context (conventions, constraints)	Every session, automatically
Workflow	Ordered sequence of skills with a fixed entry point	Loaded as a rule — always active
MCP server	Exposes pipelines, tables, and secrets as tools	During a session, via MCP protocol
dltHub context	9,700+ REST API source definitions with verified connectors and pipeline patterns	During source discovery, via search_dlthub_sources

MCP tools

Two MCP servers give the agent structured context throughout the workflow to avoid the need for manual copy-pasting.

dlt-workspace-mcp (local, installed by dlt ai init) exposes: data inspection tools (list_tables, preview_table, execute_sql_query, get_row_counts, display_schema, get_local_pipeline_state), secrets tools (secrets_view_redacted, secrets_update_fragment), and toolkit discovery (list_toolkits, toolkit_info).

dltHub context (remote) provides search_dlthub_sources — used by the find-source skill to search 9,700+ REST API source definitions and return verified connectors with reference links before writing code.

Available toolkits

Toolkit	Phase	Workflow entry	What it does	Example prompts	Availability
bootstrap	Setup	/init-workspace	Checks for uv, Python venv, and dlt; installs what's missing; then runs dlt ai init and lists available toolkits	"Run /init-workspace to set up a Python environment with dlt"	Try it out yourself! Run /init-workspace
rest-api-pipeline	Build	find-source	Scaffold, debug, and validate REST API ingestion pipelines	"Use find-source to load data from the Stripe API into DuckDB"	Try it out yourself! Run /find-source
data-exploration	Explore	explore-data	Query loaded data and create marimo dashboards	"Use explore-data to explore my Stripe pipeline and create a dashboard"	Try it out yourself! Run /explore-data
dlthub-runtime	Run	setup-runtime	Deploy pipelines to the dltHub platform	"Use setup-runtime to deploy my pipeline to dltHub"	Join early access
transformations	Transform	annotate-sources	Design a Canonical Data Model (CDM) and write dlt transformation functions from existing pipelines	"Use annotate-sources to start building a CDM from my HubSpot and Luma pipelines"	Join early access

init is a shared dependency that provides rules, secrets handling, and the MCP server. It is installed automatically by dlt ai init or as a separate plugin via the Claude marketplace.

Getting started

Note: All dlt ai commands below use uv run dlt ... syntax. If you have dlt installed globally or in an active virtual environment, you can omit uv run and call dlt directly. We recommend using uv.

Installation

# Install uv (fast Python package manager) if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install dlt with workspace support
uv pip install --upgrade "dlt[workspace]"

# If you intend to use the transformations toolkit, also install:
uv pip install "dlt[hub]"

# Set up your workspace (auto-detects your coding assistant)
uv run dlt ai init

# If multiple coding assistants are detected, specify one explicitly:
uv run dlt ai init --agent <agent>  # <agent>: claude | cursor | codex

dlt ai init detects your coding assistant from environment variables and config files, then installs skills, rules, and the MCP server in the correct locations for that tool.

Claude Code note: Add the following to your CLAUDE.md to enforce safe credential handling:

CRITICAL: never ask for credentials in chat. Always let the user edit secrets directly and do not attempt to read them.

Cursor note: After running the command, manually enable the dlt-workspace-mcp server in Cursor Settings > MCP. Add the following to your .cursor/rules/security.mdc to enforce safe credential handling:

CRITICAL: never ask for credentials in chat. Always let the user edit secrets directly and do not attempt to read them.

Codex note: Codex does not support commands and rules, so the installer converts those into skills and AGENTS.md. Codex also runs in a strict sandbox — consider enabling web access in your project or global config:

# .codex/config.toml
web_search = "live"

Add the following to your AGENTS.md to enforce safe credential handling:

CRITICAL: never ask for credentials in chat. Always let the user edit secrets directly and do not attempt to read them.

Browse and install toolkits

No Python environment yet? The bootstrap toolkit (installed above) sets up uv, Python, and dlt for you — run /init-workspace to get started.

uv run dlt ai toolkit list

Install toolkits (if you are not sure which toolkits to install we recommend installing all of them):

uv run dlt ai toolkit bootstrap install
uv run dlt ai toolkit rest-api-pipeline install
uv run dlt ai toolkit dlthub-runtime install
uv run dlt ai toolkit data-exploration install
uv run dlt ai toolkit transformations install

Starting the workbench

Use one of the example prompts from the Available toolkits table above to kick off a workflow.

Claude Code — start a new session via claude in your terminal. Restart after installation for skills and MCP to take effect.

Cursor — open the project in Cursor and use the chat panel (Cmd+L). The installed skills and rules are picked up automatically.

Codex — launch the Codex CLI via codex or use the Codex chat in the UI. Restart Codex after setup for the MCP server to take effect.

Claude Code marketplace plugin (Early Access)

Early Access: The Claude Code plugin is currently in early access and may not provide the best linking experience between different toolkits. We recommend using the dlt ai CLI above for the most up-to-date experience.

The workbench is also available as a Claude Code plugin via the marketplace. Start a Claude Code session and run:

/plugin marketplace add dlt-hub/dlthub-ai-workbench
/plugin install init@dlthub-ai-workbench --scope project
/plugin install bootstrap@dlthub-ai-workbench --scope project
/plugin install rest-api-pipeline@dlthub-ai-workbench --scope project
/plugin install dlthub-runtime@dlthub-ai-workbench --scope project
/plugin install data-exploration@dlthub-ai-workbench --scope project
/plugin install transformations@dlthub-ai-workbench --scope project

Start a new session — plugins take effect only after restarting Claude Code: claude

Resuming a session? Plugins installed mid-session are not active until you start a new one.

The dlt ai CLI

The dlt ai subcommand is the bridge between the workbench and your coding assistant. dlt ai init installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. dlt ai toolkit install copies additional toolkit components (skills, rules, commands) into the right locations for your assistant.

Toolkit management — copies skills, rules, commands, and MCP config from the workbench into your project's agent config directory (.claude/, .cursor/, .agents/, etc.):

uv run dlt ai status                        # show installed agent, dlt version, active toolkits
uv run dlt ai toolkit list                  # list available toolkits from the workbench
uv run dlt ai toolkit <name> info           # show a toolkit's skills, commands, and workflow
uv run dlt ai toolkit <name> install        # install a toolkit for the detected agent
uv run dlt ai toolkit <name> install --agent <agent>  # <agent>: claude | cursor | codex  - override agent detection

Secrets management — dlt stores credentials in TOML files; these commands let the assistant inspect and update them without reading raw secret values:

uv run dlt ai secrets list                  # show which secret files exist and where
uv run dlt ai secrets view-redacted         # print secrets with values masked
uv run dlt ai secrets update-fragment --path <file> '<toml>'  # merge a TOML snippet into a secrets file

MCP server — starts a local server that exposes your dlt workspace (pipelines, schemas, tables, secrets) as tools the assistant can call:

uv run dlt ai mcp run                       # run in SSE mode (default)
uv run dlt ai mcp run --stdio               # run in stdio mode (for assistants that require it)
uv run dlt ai mcp install                   # register the MCP server in the agent's config

The MCP server allows the assistant to answer questions like "what tables were loaded?" or "show me the schema" without you having to copy-paste output into the chat.

License

This project is licensed under the dltHub AI Workbench License.