@astramindapp/mcp-server 0.13.0 → 0.13.1
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 +42 -10
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
# @astramindapp/mcp-server
|
|
2
2
|
|
|
3
|
-
**MIND MCP Server** — The most complete AI memory layer available. 24 tools,
|
|
3
|
+
**MIND MCP Server** — The most complete AI memory layer available. 24 tools, 147 actions.
|
|
4
4
|
|
|
5
|
-
Your AI agents forget everything between sessions. MIND fixes that. Connect any MCP-compatible agent to your personal knowledge graph — with emotional intelligence, CRM, life management, site-wide assignable tasks, social features, self-training, autonomous insights, an admin-only Agent Command Center with per-agent ticket queues, and more.
|
|
5
|
+
Your AI agents forget everything between sessions. MIND fixes that. Connect any MCP-compatible agent to your personal knowledge graph — with emotional intelligence, CRM, life management, site-wide assignable tasks, social features, self-training, autonomous insights, an admin-only Agent Command Center with per-agent ticket queues, an admin-only **Featured Minds Portal** (curate the public marketplace at `m-i-n-d.ai` from any MCP client — model, public chat prompt, temperature, brand fields, write-through to the linked user's profile), and more.
|
|
6
6
|
|
|
7
7
|
**Self-describing.** Every connecting client receives a full integration briefing in the MCP `initialize` response, and can read the complete playbook from the `mind://integration-guide` resource — so any agent knows what MIND is, which integration path fits its runtime (MCP server / OpenClaw plugin / REST API), how to authenticate, and the session protocol, without being told.
|
|
8
8
|
|
|
@@ -18,7 +18,7 @@ Your AI agents forget everything between sessions. MIND fixes that. Connect any
|
|
|
18
18
|
| `mind_crm` | 7 | Contacts, pipeline, activity logging, interaction history |
|
|
19
19
|
| `mind_tasks` | 9 | Site-wide tasks — assignable, completable work items on projects, contacts, or agents, plus completion reports |
|
|
20
20
|
| `mind_graph` | 3 | Graph stats, diagnostics, entity labels |
|
|
21
|
-
| `mind_admin` |
|
|
21
|
+
| `mind_admin` | 11 | **Admin-only.** User provisioning + the **Featured Minds Portal**: full CRUD over the public marketplace (get_full / update / update_owner_profile / reorder / delete), tier/credit management |
|
|
22
22
|
| `mind_sense` | 7 | MINDsense emotional intelligence — state, signals, timeline, KG weights, spikes |
|
|
23
23
|
| `mind_research` | 3 | Launch autonomous deep research jobs |
|
|
24
24
|
| `mind_train` | 7 | Self-training sessions + save chats to knowledge graph |
|
|
@@ -297,16 +297,48 @@ mind_tasks({ action: "reports" })
|
|
|
297
297
|
| `mark_read`, `mark_all_read` | Read management |
|
|
298
298
|
| `stats` | Notification overview |
|
|
299
299
|
|
|
300
|
-
### `mind_admin` — Administration
|
|
300
|
+
### `mind_admin` — Administration & Featured Minds Portal
|
|
301
|
+
|
|
302
|
+
Requires an admin-scoped MIND API key. Powers everything at `https://m-i-n-d.ai/#/admin/featuredmindsportal` — the same surface any MCP client (Claude Code, Cursor, Windsurf, n8n via MCP, custom agents) can drive end-to-end.
|
|
303
|
+
|
|
304
|
+
#### User provisioning + tier/credits
|
|
305
|
+
| Action | Description |
|
|
306
|
+
|--------|-------------|
|
|
307
|
+
| `create_user` | Provision new MIND account; optionally generate an API key |
|
|
308
|
+
| `list_users` | List users with analytics, filterable by activity window and `source` tenant |
|
|
309
|
+
| `update_user_tier` | Change subscription tier (free / pro / enterprise) |
|
|
310
|
+
| `adjust_user_credits` | Add (+) or deduct (–) credits |
|
|
311
|
+
|
|
312
|
+
#### Featured Minds Portal — full CRUD
|
|
313
|
+
The catalog (`featured_minds` collection) and the linked owner profile (`user_profiles`) edited together so changes hit `https://m-i-n-d.ai/m/{username}` immediately.
|
|
301
314
|
|
|
302
315
|
| Action | Description |
|
|
303
316
|
|--------|-------------|
|
|
304
|
-
| `
|
|
305
|
-
| `
|
|
306
|
-
| `
|
|
307
|
-
| `
|
|
308
|
-
| `
|
|
309
|
-
| `
|
|
317
|
+
| `create_featured_mind` | Promote a user's MIND into the featured catalog |
|
|
318
|
+
| `list_featured_minds` | List every featured mind with `mind_id`, `display_order`, `featured`, `is_public` |
|
|
319
|
+
| `get_featured_mind_full` | Bundled view in one round-trip: featured_mind doc + linked user_profile + available_models catalog (what the portal side sheet loads) |
|
|
320
|
+
| `update_featured_mind` | Catalog fields: `title`, `subtitle`, `description`, `tags`, `featured`, `display_order`, `is_public`, `avatar_url`, `banner_url`, `price` |
|
|
321
|
+
| `update_featured_mind_owner_profile` | **Write-through to user_profiles** for the linked user: `preferred_llm_model`, `public_mind_prompt` (≤3000 chars), `chat_temperature` (0.0–2.0), `chat_reasoning_effort` (minimal/low/medium/high, thinking models only), `public_mind_enabled`, `public_mind_tagline`/`greeting`/`persona`, `bio`, `avatar_url`, `banner_url`. Pass `null` on `preferred_llm_model` to clear and fall back to platform default. |
|
|
322
|
+
| `reorder_featured_minds` | Bulk display_order via `ordered_mind_ids: string[]` — index in list becomes the order. Idempotent. |
|
|
323
|
+
| `delete_featured_mind` | Remove from catalog. The user's underlying MIND is preserved. |
|
|
324
|
+
|
|
325
|
+
##### Recipe — change a featured MIND's model + prompt from MCP
|
|
326
|
+
```
|
|
327
|
+
mind_admin({ action: "list_featured_minds" })
|
|
328
|
+
// → grab the mind_id you want
|
|
329
|
+
|
|
330
|
+
mind_admin({ action: "get_featured_mind_full", mind_id: "<id>" })
|
|
331
|
+
// → see current owner_profile + the full available_models catalog
|
|
332
|
+
|
|
333
|
+
mind_admin({
|
|
334
|
+
action: "update_featured_mind_owner_profile",
|
|
335
|
+
mind_id: "<id>",
|
|
336
|
+
preferred_llm_model: "anthropic/claude-sonnet-4.6",
|
|
337
|
+
chat_temperature: 0.7,
|
|
338
|
+
public_mind_prompt: "You are Anthony's public MIND. Answer in his voice."
|
|
339
|
+
})
|
|
340
|
+
// → next anonymous chat at /m/{username} uses the new model + prompt + temp
|
|
341
|
+
```
|
|
310
342
|
|
|
311
343
|
### `mind_agents` — Agent Command Center (Admin)
|
|
312
344
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@astramindapp/mcp-server",
|
|
3
|
-
"version": "0.13.
|
|
3
|
+
"version": "0.13.1",
|
|
4
4
|
"mcpName": "io.github.theastraway/mind",
|
|
5
5
|
"description": "MIND MCP Server — 24 tools, 147 actions. The most complete AI memory layer with document folders, the MIND Sense Front Layer (16 typed-document templates), Agent Command Center (admin-only registry of every agent across the Astra AI fleet — heartbeat, probe, status, ownership & sharing), agent ticket queues (file, answer, triage, resolve client feedback and bugs), Featured Minds Portal (full admin CRUD over the public marketplace — model picker, public chat prompt, temperature, brand fields, write-through to user_profiles), multi-MIND accounts (own and switch between many knowledge graphs), site-wide assignable tasks, personal knowledge graph with emotional intelligence, CRM, life management, social, self-training, research agent, automations. Works with Claude, GPT, Gemini.",
|
|
6
6
|
"files": [
|