embrasure-data11.6 KB
View saved version →
---
name: embrasure-data
description: Set up a data warehouse and analytics from one prompt, connect sources, reach a verified first answer, and build dashboards with Embrasure.
---
# Embrasure: one-prompt warehouse and analytics
Use the Embrasure tools for the connected workspace. Keep the user-facing name Embrasure.
Never ask for warehouse passwords, API keys, or session tokens in chat; use browser connection links.
## Start with the user's first question
Use the installed MCP connection. Do not send an already connected user through
installation again or require an external setup guide. Start with `warehouse_status`
and `sources_list` in the intended workspace. If the Embrasure tools are missing, or a
call says “Connect Embrasure to continue”, follow “When the Embrasure tools are missing” below.
For a new warehouse, inspect `warehouse_plan` and apply the requested setup. Inspect
source types, connect the requested sources through browser handoffs, then plan and
start ingestion using the supported mode. Default to all accessible, supported tables
unless the user specifies a narrower scope; preserve explicit exclusions and selections.
Reuse existing workspace, source, and ingestion handles rather than creating duplicates.
Continue until ingested data can be queried. Use the catalog's qualified relation names,
run the user's first query, and return the result with evidence. For a dashboard request,
create the requested charts and dashboard, read them back, and verify the chart queries.
Ask only for missing information, browser sign-in, source access, or a decision the user
needs to make. Report pending or blocked sources without claiming they are ready.
“Get started in 30 seconds” describes starting setup. Source sync time depends on the
data. A connected source or running sync is not a completed answer. Verify query results
and report ready, pending, and blocked sources before claiming analytics are ready.
For an existing warehouse, go straight to the requested question or dashboard.
## When the Embrasure tools are missing
Some clients, including Codex, hide MCP startup and sign-in failures from the agent.
Missing tools alone do not show that sign-in is needed. If the client loads tools on
demand, search for the Embrasure tools first. If they are still missing, find the
client's entry whose URL is `https://embrasure.ai/api/mcp`, and use its listed name:
- Codex: `codex mcp list`. Read the Status column first, then Auth.
- Claude Code: `claude mcp list`. Plugin installs list `plugin:embrasure:embrasure`.
- No shell, ChatGPT, or Cursor: ask the user what Embrasure shows in the client's MCP
or app settings (ChatGPT: Settings, then Apps; Cursor: Cursor Settings, then MCP).
Tell the user which case applies:
- **Installed, needs sign-in.** Codex: Status `enabled` and Auth `Not logged in`.
Claude Code: `Needs authentication`. A tool call that says “Connect Embrasure to
continue” means the same. Offer to reconnect right away (see below).
- **Not installed or disabled.** No entry, Codex Status `disabled`, or Claude Code
`Disabled for this project`. Offer to install or enable the Embrasure plugin
(Claude Code: re-enable it in `/mcp`). Don't start a login for it.
- **Status unclear.** Codex Auth `Unknown`, Claude Code `Failed to connect`, a missing
command, or a sandboxed shell without network access. Don't call the user signed in
or signed out. Rerun the check with network access, or ask the user to run it in
their own terminal.
- **Signed in, tools still missing.** Codex Auth `OAuth`. Check whether Embrasure is up:
```sh
curl -sS -m 10 -o /dev/null -w '%{http_code}\n' https://api.embrasure.ai/health
curl -sS -m 10 -o /dev/null -w '%{http_code}\n' -X POST -H 'Content-Type: application/json' -d '{}' https://embrasure.ai/api/mcp
```
`200` then `401` means Embrasure is up. The `401` only shows the endpoint is
reachable, not why your client's sign-in failed. The saved sign-in is probably no
longer Preview of the first 4,000 characters. Read full instructions →
