What you can build with DataUnmess

Dashboards

Publish live business views from one prompt.

Build KPI cards, trends, comparisons, funnels, maps, tables, and written insights from connected data. Saved cards retain their source query, so opening or refreshing a dashboard does not require another AI generation step.

25 chart types with labels, legends, formats, colors, axes, sorting, and saved filters
Query-backed refresh from datasets, databases, Google Sheets, and imported SaaS data
Shared workspace folders, dashboard themes, editing, and reusable chart settings

Explore AI dashboards

Data Pipelines

Turn messy sources into reliable, refreshable datasets.

Import, filter, deduplicate, join, reshape, enrich, and publish data through a saved pipeline. DataUnmess chooses connector-native imports, SQL pushdown, or Python according to the source, destination, and transformation.

Managed imports from GA4, HubSpot, Google Sheets, files, APIs, and databases
Preview, validation, run history, logs, schedules, repair windows, and backfills
Publish to DataUnmess managed Postgres or a table in your own database

Explore AI data pipelines

Data Science

Explore drivers and patterns without starting from a blank query.

Ask business questions in plain language, then inspect the supporting queries, segments, aggregations, and visual evidence. Save useful charts and analysis in the same workspace as operational dashboards.

Aggregate, filter, pivot, compare cohorts, and inspect trends
Pair written analysis with source-backed supporting charts
Reuse connected data, prepared pipeline outputs, and workspace context

Open Data Science

DataUnmess Memory

Give every connected AI the same business context.

Store company context, products, glossary terms, KPI definitions, and data catalog knowledge in an agent-readable workspace. Future dashboard, pipeline, and analysis requests can reuse that shared language.

Company, product, glossary, KPI, and catalog knowledge
Context shared across Codex, Claude Code, Cursor, and other MCP clients
Readable workspace memory that survives beyond a single conversation

Read about Memory

Which surface should I use?

Every tool below is the same tool — only the way you call it differs. MCP is AI-driven (a model in your client decides when to call which tool). Shell CLI is not — you call commands directly from a terminal or script. Chat is the in-app surface at DataUnmess Studio.

MCP

Hosted MCP endpoint for your AI client.

Paste our hosted endpoint and a workspace-scoped MCP key into Codex Desktop, Claude Code, Gemini, Claude Desktop, Cursor, Windsurf, ChatGPT, or any MCP-compatible client. Their AI then invokes DataUnmess tools on your behalf — no in-app tokens.

Pick this when: You already pay for an AI subscription and want it to drive DataUnmess.

Shell CLI

Headless commands. No AI involved.

Run dash-ai query, dash-ai chart, dash-ai transforms run directly in your terminal. Deterministic, scriptable, perfect for cron jobs and CI pipelines. Only a subset of tools have a direct CLI.

Pick this when: You want scheduled jobs or scripted automation. The AI is not in the loop.

Chat (in-app)

Natural language inside DataUnmess Studio.

Open DataUnmess Studio, type what you want, and the AI calls the tools below. The friendliest path, but the programmatic surfaces above are more battle-tested for serious workflows.

Pick this when: You want a quick exploration without configuring an external client.

Tool matrix

Each row is one tool. Cells show how to invoke it on each surface. ✓ available · excl intentionally excluded · — not applicable

Tool	MCP	Chat	Shell CLI	What it does
Charts & theming
build_chart	✓	✓	dash-ai chart	Create a chart from a dataset query.
update_chart	✓	✓	dash-ai charts update	Edit an existing chart's title, type, or fields.
remove_chart	excl	✓	excl	Delete a chart. Chat-only — destructive ops need conversational confirmation.
set_theme	✓	✓	dash-ai theme set	Apply a theme preset to the active dashboard.
set_category_colors	✓	✓	dash-ai theme colors	Pin specific colors to category values across charts.
set_dashboard_filter	✓	✓	dash-ai dashboards filter	Set, merge, or clear saved dashboard date and category filters.
build_analysis	✓	✓	dash-ai analysis build	Add a written analysis card alongside the charts.
Data & connections
query_data	✓	✓	dash-ai query	Query an imported dataset (CSV/Excel/Sheets snapshot).
query_connection	✓	✓	dash-ai connections query	Run a SELECT against a connected database or warehouse (Postgres/MySQL/ClickHouse).
query_google_sheets	✓	✓	dash-ai sheets read	List spreadsheets and read ranges from a live Google Sheets connection.
create_connection	✓	✓	dash-ai connections create	Return a deep-link to add a new connection. Never accepts credentials directly.
Flowcharts
build_flowchart	✓	✓	dash-ai flowcharts build	Create a flowchart from nodes/edges or Mermaid.
update_flowchart	✓	✓	dash-ai flowcharts update	Add, remove, or rename nodes and edges.
duplicate_flowchart	✓	✓	dash-ai flowcharts duplicate	Copy the current flowchart under a new name.
remove_flowchart	excl	✓	excl	Delete a flowchart. Chat-only — destructive ops need conversational confirmation.
Data Pipelines
build_transform_flow	✓	✓	dash-ai transforms build	Author a pipeline. Connected imports use connector-native queries; same-DB routes to SQL pushdown, mixed/GA4/API routes to Python.
validate_transform_flow	✓	✓	dash-ai transforms validate	Dry-compile and sample-run a pipeline. Returns per-step SQL and sample rows.
run_transform_flow	✓	✓	dash-ai transforms run	Execute a pipeline and write to its configured sink.
get_transform_run	✓	✓	dash-ai transforms run-info	Inspect a single run — per-step status and compiled SQL on failure.
list_transform_runs	✓	✓	dash-ai transforms runs	List recent runs, optionally filtered by pipeline.
Workspace
update_flow	✓	✓	dash-ai flows update	Rename and/or move a flowchart between folders.
update_dashboard	✓	✓	dash-ai dashboards update	Rename and/or move a dashboard between folders.
update_transformation	✓	✓	dash-ai transformations update	Rename and/or move a pipeline between folders.
Chat affordance
call_mcp_tool	excl	✓	excl	Invoke a tool on a connected third-party MCP server. Chat-only — prevents MCP-in-MCP recursion.
suggest_next_steps	excl	✓	excl	Render clickable follow-up buttons in the DataUnmess chat panel. Chat-only — UI affordance.

Advanced: the MCP server is hosted on our Vercel endpoint by default. You can also self-host it locally with dash-ai serve — same tools, same protocol, runs on your machine.

Shell CLI extras

The shell CLI also exposes read-only listing and admin commands that aren't AI tools — useful for scripting and inspection.

dash-ai datasets list	List all imported datasets in the workspace.
dash-ai datasets info <name>	Show columns, row count, and a sample of a dataset.
dash-ai connections list	List all configured data connections.
dash-ai flows list	List flowcharts in the workspace.
dash-ai dashboards list	List dashboards in the workspace.
dash-ai transforms list	List pipelines in the workspace.
dash-ai serve [--http] [--port 3100]	Self-host the MCP server locally (alternative to the Vercel-hosted endpoint).

Add -f json, -f table, or -f compact to any command to control output format.

FAQ

Do I need an account to use these tools?

Yes for any surface that touches your data: MCP, Shell CLI, and Chat all require a DataUnmess workspace. The Chat surface uses your browser session; MCP and the Shell CLI use a workspace-scoped key issued from your account settings.

Where does the MCP server actually run?

Hosted at https://app.dataunmess.ai/api/mcp (the MCP route lives inside the same Next.js app on Railway — separate subdomain not needed). For local dev, run `pnpm dev:mcp` and point your AI client at http://localhost:3100/mcp.

Why is remove_chart chat-only?

Destructive operations (remove_chart, remove_flowchart) need conversational context to confirm intent before deleting. The web chat can ask 'are you sure?' and remember the answer; external MCP clients cannot reliably do that. We exclude these from MCP rather than risk an AI deleting work without confirmation.

Can I use my existing Claude / Gemini / ChatGPT subscription?

Yes. Add our hosted MCP endpoint plus a workspace-scoped MCP key to Codex Desktop, Claude Code, Gemini, Claude Desktop, Cursor, Windsurf, ChatGPT, or any MCP-compatible client. Their AI then drives DataUnmess tools using tokens from your subscription. No in-app AI tokens consumed. See the Connect your AI page for setup steps.

When should I use the shell CLI instead of MCP?

Use the shell CLI for scheduled jobs, CI pipelines, and scripts where you don't want an AI in the loop. The CLI is deterministic — same command, same output. MCP is for humans collaborating with an AI; the CLI is for machines following a script.

Some tools show 'gap' — what does that mean?

A gap is a tool we plan to support on that surface but haven't shipped yet. Gaps are tracked in TOOL_PARITY.md and addressed in priority order. Raw dataset upload is intentionally not an AI/MCP tool; use the web UI or `dash-ai datasets upload <file>` for local files, and use Data Pipelines for connected-source imports.

Dashboards, pipelines, analysis, and business memory