mcpHosted AI, explicit consent

Generate content

tools/call

Generate a LinkedIn post using the workspace voice config, content examples, and intelligence context. The route requires workspace_id as a query param (auto-injected from the API key when present). Returns hook + body + cta + alternatives + reasoning.

Parameters

workspaceId

string

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

workspace_id

string

Workspace UUID (sent as ?workspace_id query param). Auto-injected with API key auth.

workspace_slug

string

Optional workspace slug for the agent context.

topicrequired

string

What the post should be about (10-5000 chars).

postType

string

No description.

thought_leadership | lead_magnet | case_study | personal_story

postLength

string

No description.

short | medium | long

linkedinAccountId

string

Optional - pin the post to a specific account voice.

hookStyle

string

No description.

regenerateInstructions

string

User feedback when iterating on a previous draft.

string

Previous post content for regeneration context.

strategyContext

object

No description.

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-content",
    "arguments": {
      "topic": "example",
      "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.