intelligence_classify_messages
intelligence_classify_messages
Section titled “intelligence_classify_messages”Category: intelligence
Classify recent messages into provided categories using the client’s LLM. Each classification carries a 0-1 confidence score.
When to use
Section titled “When to use”triage spam vs. question vs. discussion; bucket support requests; segment conversations.
When NOT to use
Section titled “When NOT to use”| Field | Type | Required | Description |
|---|---|---|---|
channel_id | string | yes | Channel to classify messages from |
categories | array | yes | Category labels (2-20) |
limit | integer | yes | Messages to classify (5-100, default 25) |
Returns
Section titled “Returns”\{classifications:[\{message_id, author, category, confidence\}], count, sampling_used\}.
Output schema
Section titled “Output schema”| Field | Type | Required | Description |
|---|---|---|---|
classifications | array | yes | |
count | number | yes | |
sampling_used | boolean | yes |
Annotations
Section titled “Annotations”| Property | Value |
|---|---|
| Read-only | yes |
| Destructive | no |
| Idempotent | yes |
| Open-world | yes |
| Confirmation required | no |
Source
Section titled “Source”packages/mcp-core/src/tools/intelligence/classify_messages.ts