@databrainhq/mcp-server 0.2.2 → 0.2.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -14
- package/dist/index.js +117 -1700
- package/dist/index.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -197,12 +197,7 @@ Prompts are guided workflows your AI assistant can follow. Ask for them by name
|
|
|
197
197
|
|--------|-------------|
|
|
198
198
|
| `embed-existing-dashboard` | Embed a dashboard you've already built in the Databrain UI |
|
|
199
199
|
| `embed-blank-dashboard` | Multi-tenant setup — each client gets their own dashboard |
|
|
200
|
-
| `enable-metric-creation` | Let end-users build metrics (drag-and-drop or AI chat) |
|
|
201
200
|
| `brand-my-embed` | Customize colors, fonts, charts, card styling, responsive layout |
|
|
202
|
-
| `localize-embed` | Multi-language support, translations, calendar format |
|
|
203
|
-
| `secure-my-embed` | Permissions, access controls, role-based guest tokens |
|
|
204
|
-
| `setup-filters` | Dashboard filters — dropdowns, date ranges, server-side filters |
|
|
205
|
-
| `manage-embeds` | List, compare, and review existing embed configurations |
|
|
206
201
|
| `query-data` | Query your data with natural language, manage the semantic layer |
|
|
207
202
|
| `populate-semantic-layer` | Auto-generate table/column descriptions to enable natural language querying |
|
|
208
203
|
|
|
@@ -210,7 +205,7 @@ Prompts are guided workflows your AI assistant can follow. Ask for them by name
|
|
|
210
205
|
|
|
211
206
|
## Tools Reference
|
|
212
207
|
|
|
213
|
-
|
|
208
|
+
21 tools organized by category. Your AI assistant picks the right tools automatically — you don't need to call them directly.
|
|
214
209
|
|
|
215
210
|
> **Note:** Infrastructure creation (datasources, datamarts, workspaces) is done in the **Databrain UI**. However, the **semantic layer** is populated via MCP tools (`get_semantic_layer`, `update_semantic_layer`) — the AI auto-generates descriptions from column names.
|
|
216
211
|
|
|
@@ -239,17 +234,15 @@ Prompts are guided workflows your AI assistant can follow. Ask for them by name
|
|
|
239
234
|
</details>
|
|
240
235
|
|
|
241
236
|
<details>
|
|
242
|
-
<summary><b>Embeds</b> (
|
|
237
|
+
<summary><b>Embeds</b> (5) — Create, configure, and customize embedded dashboards</summary>
|
|
243
238
|
|
|
244
239
|
| Tool | Description |
|
|
245
240
|
|------|-------------|
|
|
246
241
|
| `create_embed` | Create an embed (standard or multi-tenant with `clientId`) |
|
|
247
242
|
| `list_embeds` | List embed configurations |
|
|
248
243
|
| `get_embed_details` | Get full embed details by ID |
|
|
249
|
-
| `update_embed` | Update embed config (
|
|
244
|
+
| `update_embed` | Update embed config — access settings, options, filters, i18n (via `body` passthrough) |
|
|
250
245
|
| `customize_embed_theme` | Presets, colors, fonts, cards, chart appearance, responsive layout |
|
|
251
|
-
| `configure_embed` | UI options, filters (string/date/number/SQL), i18n, translations |
|
|
252
|
-
| `diagnose_embed_health` | Diagnose malformed embeds + validate runtime readiness |
|
|
253
246
|
</details>
|
|
254
247
|
|
|
255
248
|
<details>
|
|
@@ -258,7 +251,7 @@ Prompts are guided workflows your AI assistant can follow. Ask for them by name
|
|
|
258
251
|
| Tool | Description |
|
|
259
252
|
|------|-------------|
|
|
260
253
|
| `generate_guest_token` | Generate a frontend guest token (server-side) |
|
|
261
|
-
| `generate_embed_code` | Generate integration code (React, Next.js, Vue, Angular, Svelte, vanilla JS) |
|
|
254
|
+
| `generate_embed_code` | Generate integration code (React, Next.js, Vue, Angular, Svelte, SolidJS, vanilla JS) |
|
|
262
255
|
</details>
|
|
263
256
|
|
|
264
257
|
<details>
|
|
@@ -272,12 +265,11 @@ Prompts are guided workflows your AI assistant can follow. Ask for them by name
|
|
|
272
265
|
</details>
|
|
273
266
|
|
|
274
267
|
<details>
|
|
275
|
-
<summary><b>Discovery
|
|
268
|
+
<summary><b>Dashboard Discovery</b> (1)</summary>
|
|
276
269
|
|
|
277
270
|
| Tool | Description |
|
|
278
271
|
|------|-------------|
|
|
279
272
|
| `list_dashboards` | List dashboards (by data app, workspace, or globally) |
|
|
280
|
-
| `setup_embed_interactive` | Guided step-by-step flow for the full embed setup |
|
|
281
273
|
</details>
|
|
282
274
|
|
|
283
275
|
---
|
|
@@ -320,7 +312,7 @@ This usually means no workspace was selected. Ask the assistant: *"List my works
|
|
|
320
312
|
|
|
321
313
|
1. Check that the guest token is generated **server-side** (never expose API tokens in frontend code)
|
|
322
314
|
2. Verify the embed ID and dashboard ID match
|
|
323
|
-
3. Ask: *"
|
|
315
|
+
3. Ask: *"Check my embed configuration for issues"* — the assistant inspects via `get_embed_details`
|
|
324
316
|
|
|
325
317
|
### Theme changes not showing
|
|
326
318
|
|