> ## Documentation Index
> Fetch the complete documentation index at: https://docs.textql.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Developer Workshop — API & MCP

> A hands-on workshop for developers and technical integrators: drive Ana programmatically through the REST API, stream responses into your apps, automate playbooks and dashboards…

A hands-on workshop for **developers and technical integrators**: drive Ana programmatically through the REST API, stream responses into your apps, automate playbooks and dashboards from code, expose Ana inside Claude/Cursor/ChatGPT via MCP, and extend Ana outward with MCP tools.

Hands-on format: copy-paste `curl`/Python, checkpoints. **\~2 hours**.

## What you'll be able to do

<CardGroup cols={2}>
  <Card title="The Chat API">Sync, SSE streaming, retrieval — the agentic loop as an endpoint.</Card>
  <Card title="Resource APIs">Connectors, playbooks, dashboards as code; the ETL-completion trigger.</Card>
  <Card title="Sandbox API">Warehouse data into DataFrames; your code in Ana's environment.</Card>
  <Card title="Ana as MCP server">Warehouse answers inside Claude, Cursor, and your IDE.</Card>
  <Card title="MCP tools">Extend Ana with Notion, GitHub, Jira — or your internal APIs.</Card>
  <Card title="Production patterns">Identity design, timeouts, cost, testing nondeterminism.</Card>
</CardGroup>

## Prerequisites

* API key access (Settings → Configuration → API Keys; creation may be role-gated)
* `curl` or Python + `requests`; an MCP client for Modules 4–5
* A connected data source

<Warning>
  API shapes follow the current reference at [docs.textql.com](https://docs.textql.com/api-reference/v2/introduction). Python SDK: `TextQLLabs/textql-python`. VPC deployments substitute their own host.
</Warning>

<Accordion title="For facilitators — running this as a guided session">
  **T-minus-1-day pre-flight:** run the workshop's key prompts end-to-end in the session workspace — confirm logins, connectors, and the features this workshop touches are enabled for every attendee; have a fallback demo workspace ready in case a customer connector fails live. **Pacing:** when a long prompt is running (2–4 min), fire it first, then discuss the concept while Ana works — never watch a spinner in silence. If behind schedule, cut sections marked optional, never the checkpoints. **Group sessions:** attendees drive, you narrate; collect every miss or wrong answer in a shared doc — that list is the ontology backlog. With 10+ attendees on one warehouse, stagger the heavy prompts.
</Accordion>