MCPMCP Tools/Social Inbox/classify_inbox_items

classify_inbox_items

Writeinbox:write

Correct sentiment, language, intent, needsResponse or spam on inbox items. Provide items or a structured filter and at least one field. Null clears a field. Pins the correction against automatic classification. Checks all selected clients before writes; never invokes the model or sends a message.

Parameters

itemsobject[]optional

kind"comment" | "message" | "mention"optional

idstringoptional

filterobjectoptional

clientIdstringoptional

locationsstring[]optional

fromstringoptional

tostringoptional

tzintegeroptional

platformstring[]optional

status("open" | "resolved")[]optional

sentiment("positive" | "neutral" | "negative")[]optional

assignee"all" | "unassigned" | "me" | "team"optional

keywordstringoptional

sort"newest" | "oldest"optional

typesstring[]optional

sourcesstring[]optional

savedbooleanoptional

tagsstring[]optional

tagMatch"any" | "all"optional

untaggedbooleanoptional

languagestring[]optional

needsResponse"yes" | "no"optional

spam"exclude" | "only"optional

priority("1" | "2" | "3" | "4" | "none")[]optional

caseType("general" | "support" | "question" | "feedback" | "lead")[]optional

poststringoptional

pulse"closing" | "reply" | "fresh"optional

sentimentoptional

languageoptional

needsResponsebooleannulloptional

intentoptional

spambooleannulloptional

Example request

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "classify_inbox_items",
    "arguments": {}
  }
}

Example response

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "..."
      }
    ]
  }
}

Response shape shown for illustration — the actual content depends on the tool and your data.