mcpHosted AI, explicit consent

Generate reply draft

tools/call

Run the ReplyAgent to draft a reply to an inbox conversation, using workspace GTM context (offers, ICP, personas, case studies) and calendar availability. Returns the drafted message, strategy, confidence, and whether it needs human review before sending.

Parameters

workspaceId

string

Optional workspace ID or slug. Required when this credential can access multiple workspaces and no workspace was configured on the client.

workspaceSlug

string

Required for Clerk auth. Ignored when using API key (workspace inferred from key).

linkedin_account_id

string

Optional connected LinkedIn account UUID used to scope calendar availability and reply context.

conversationrequired

object

Required. The conversation object (must include chat_id).

messages

object[]

Message thread the reply should respond to.

sentimentAnalysis

object

Optional prior sentiment classification (from analyze-sentiment) to ground strategy selection.

allowHostedAi

boolean

Must be true when this operation uses Pipeline hosted inference.

Example

MCP tools/calljson

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "generate-reply-draft",
    "arguments": {
      "conversation": {},
      "allowHostedAi": true
    }
  }
}

Response

The operation is available, but its typed response schema has not been published yet.

JSON-RPC errors

-32602: Invalid parameters. Field-level details are returned in the JSON-RPC error data.
-32001: Authentication or hosted AI consent is required.
-32003: Workspace access is denied.
-32029: The request was rate limited.