Skip to Content
GrowSocialelion API
Research endpoints

Propose a voice profile

Distill a PROPOSED voice profile from the brand's real posts on a connected network (omit platform for the brand's primary).

POST /api/v1/refresh_voice_profile · MCP tool refresh_voice_profile · scope research + spend

Distill a PROPOSED voice profile from the brand's real posts on a connected network (omit platform for the brand's primary). It starts a model run, which costs credits, so the key needs the `spend` scope as well as `research`. X reads cost API credits; Bluesky and Mastodon reads are free. It does NOT save anything: the proposal comes back under `untrusted` for a person to review. A person applies a voice in the dashboard — ask the agent there to refresh the voice profile, or put the style notes they want into Brand settings > Identity > Tone rules. An MCP call cannot change what later drafting runs read. Nothing is published.

Scope. Scan a network for reply targets and propose a voice profile. These read networks and can cost credits. Every call costs credits, so the key also needs spend.

Arguments

NameTypeRequiredDescription
platform"x" | "bluesky" | "mastodon" | "pixelfed" | "telegram" | "devdotto" | "discord" | "ghost" | "lemmy" | "nostr" | "tumblr" | "wordpress" | "misskey" | "qiita" | "tabnews" | "youtube" | "dailymotion" | "tiktok" | "hashnode" | "peertube" | "dribbble" | "slack" | "wykop" | "plurk" | "kick" | "twitch" | "hatena" | "line"NoWhich connected network to read (a platform id from get_capabilities, e.g. "x", "bluesky"). Omit for the primary.

Request

curl -X POST https://growsocialelion.com/api/v1/refresh_voice_profile \
  -H "Authorization: Bearer gse_mcp_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Response

200 with the tool's answer. The shape below is generated from the output schema; real answers can carry more fields.

{
  "status": "string",
  "reason": "string"
}

Errors use the shared body. See Errors. The full schema is in the API reference.