@adrata/adrata-mcp 1.0.40 → 1.0.41
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/package.json +1 -1
- package/server.json +2 -2
- package/skills/qa-the-card/SKILL.md +13 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@adrata/adrata-mcp",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.41",
|
|
4
4
|
"description": "Adrata MCP Server \u2014 connect Claude Code, Codex, Gemini, Cursor, and other AI tools to your CRM. About 275 tools registered at startup for companies, people, deals, actions, buyer groups, warm intros, webhooks and intelligence, plus 65 more behind eight named toolsets you load with enable_toolset.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "server.js",
|
package/server.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
"name": "com.adrata/adrata-mcp",
|
|
4
4
|
"description": "Adrata revenue-intelligence MCP server: companies, people, opportunities, actions, buyer groups, enrichment, email, and workspace operations for AI agents.",
|
|
5
5
|
"status": "active",
|
|
6
|
-
"version": "1.0.
|
|
6
|
+
"version": "1.0.41",
|
|
7
7
|
"websiteUrl": "https://adrata.com/developers",
|
|
8
8
|
"repository": {
|
|
9
9
|
"url": "https://github.com/adrata/adrata",
|
|
@@ -15,7 +15,7 @@
|
|
|
15
15
|
"registryType": "npm",
|
|
16
16
|
"registryBaseUrl": "https://registry.npmjs.org",
|
|
17
17
|
"identifier": "@adrata/adrata-mcp",
|
|
18
|
-
"version": "1.0.
|
|
18
|
+
"version": "1.0.41",
|
|
19
19
|
"transport": {
|
|
20
20
|
"type": "stdio"
|
|
21
21
|
},
|
|
@@ -186,6 +186,19 @@ does not establish that the screen is visually correct.
|
|
|
186
186
|
by this bridge` line in the playback evidence, then close the bridge. If that
|
|
187
187
|
line is the WARNING instead, the bridge sent no policy and the playback it
|
|
188
188
|
showed says nothing about the deployed one.
|
|
189
|
+
- The pool the bridge asks for is usually the one you are already running on.
|
|
190
|
+
Call `workspace_status` first: when it reports `authSource: "stored_pool"`, an
|
|
191
|
+
`identityPool`, and `apiBase: https://api.adrata.com`, that named pool is a
|
|
192
|
+
canonical QA identity — run the bridge under that `ADRATA_MCP_IDENTITY_POOL`
|
|
193
|
+
and the `ADRATA_MCP_CONFIG_DIR` your server was started with. Holding only a
|
|
194
|
+
staging lane session (`qa:lanes`) does not mean the fleet holds no canonical
|
|
195
|
+
credential; two lanes declared a canonical playback journey owner-only on
|
|
196
|
+
2026-09-11 while running on pool `qa1` against the canonical API.
|
|
197
|
+
- The bridge binds to ONE card and serves only that card's receipts. When a
|
|
198
|
+
criterion names "the original QA video", bridge the card that CARRIES that
|
|
199
|
+
receipt — `list_work_item_qa_evidence` on the card where the journey was
|
|
200
|
+
recorded — not the card whose criterion you are executing. Bridging a card
|
|
201
|
+
with zero receipts shows no video, and that is not a playback failure.
|
|
189
202
|
|
|
190
203
|
## Manage cards as outcomes, not bug counters
|
|
191
204
|
|