secondbrainos-mcp-server 1.8.1 → 1.8.2
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 +1 -1
- package/build/index.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -156,7 +156,7 @@ Credentials are stored securely at `~/.secondbrainos/credentials.json` (created
|
|
|
156
156
|
|
|
157
157
|
4. **ListPrompts trigger**: Claude Code automatically calls `ListPrompts` on connect. This is when the first credits are spent:
|
|
158
158
|
- `runPromptChain` is called with `{}` → returns all user workflows with prompt metadata (name, order, description)
|
|
159
|
-
- `getAIAgentsSchema` is called with `{include_sensitive_config:
|
|
159
|
+
- `getAIAgentsSchema` is called with `{include_sensitive_config: true}` → returns all user agents with behaviour, knowledge collection ID, actions, and workflows
|
|
160
160
|
5. **In-memory cache**: Both responses are normalized (consistent field names, defaults applied) and sorted (prompts ordered by `order` field), then stored in memory as `cachedWorkflows`, `cachedAgents`, and name-to-ID lookup maps
|
|
161
161
|
6. **Slash commands exposed**: The cached data is surfaced as MCP prompts — `/secondbrainos:skill_*`, `/secondbrainos:agent_*`, `/secondbrainos:start_secondbrainos`, and `/secondbrainos:knowledge_bases`
|
|
162
162
|
|
package/build/index.js
CHANGED
|
@@ -444,7 +444,7 @@ class SecondBrainOSServer {
|
|
|
444
444
|
}
|
|
445
445
|
const url = `${this.baseUrl}${this.getAIAgentsSchemaPath}`;
|
|
446
446
|
const response = await axios.post(url, {
|
|
447
|
-
include_sensitive_config:
|
|
447
|
+
include_sensitive_config: true
|
|
448
448
|
}, {
|
|
449
449
|
headers: {
|
|
450
450
|
'Authorization': `Bearer ${this.userId}:${this.userSecret}`,
|