Pacifica Beauty MCP server for AI agents

Let Claude, ChatGPT or your own agent read Pacifica Beauty: 1 typed function through one MCP server. No Pacifica Beauty API key needed.

Functions
1
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just Pacifica Beauty

An MCP server for Pacifica Beauty alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.

https://api.bowmark.ai/mcp/site/pacificabeauty
Every site

One MCP server for Pacifica Beauty and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.

Functions

Open a function to see its arguments, what it returns and how to call it.

Read 1
  • getHairRecommendationRuns Pacifica's own hair-quiz recommendation engine (the Tangent AI-powered quiz at pacificabeauty.com/pages/hair-quiz) for a real set of answer tags…

    Arguments

    NameTypeRequired
    arg{ tags: string[] }Yes

    Returns PacificabeautyRecommendation

    interface PacificabeautyRecommendedProduct {
      name: string;
      price: string | null;
      url: string;
    }
    
    interface PacificabeautyRecommendation {
      products: PacificabeautyRecommendedProduct[];
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/pacificabeauty/getHairRecommendation

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.pacificabeauty.getHairRecommendation({
      tags: [
        "hair_type_straight",
        "hair_texture_fine",
        "scalp_type_dry",
        "hair_goal_deep_clean"
      ]
    });

Use it from code