Tatcha MCP server for AI agents
Let Claude, ChatGPT or your own agent read Tatcha: 2 typed functions through one MCP server. No Tatcha API key needed.
- Site
- tatcha.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Tatcha
An MCP server for Tatcha 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/tatchaEvery site
One MCP server for Tatcha and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth 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 2
getPersonalizedRitualRuns a shopper's real answers (skin type, up to three benefits, optional eye concerns, sensitivity, already-owned products) through Tatcha's own…Arguments
Name Type Required skinTypestringYes benefitsstring[]Yes eyeConcernsstring[]No sensitivebooleanNo ownedstring[]No Returns
TatchaRitualinterface TatchaRitualProduct { step: string; sku: string; name: string; secondaryName: string; price: string; handle: string; url: string; image: string; usageTime: "AM" | "PM" | "both"; description: string; inStock: boolean; } interface TatchaRitual { summary: string; products: TatchaRitualProduct[]; handoffUrl: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/tatcha/getPersonalizedRitualCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.tatcha.getPersonalizedRitual("oily", ["brightening"]);import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.tatcha.getPersonalizedRitual("oily", ["brightening"]))curl -X POST https://api.bowmark.ai/v1/sites/tatcha/getPersonalizedRitual \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"skinType":"oily","benefits":["brightening"]}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.tatcha.getPersonalizedRitual("oily", ["brightening"]);getRitualQuizOptionsReads the live "Ritual Finder" quiz's real input menus.Arguments
None.
Returns
TatchaRitualQuizOptionsinterface TatchaQuizOption { value: string; label: string; } interface TatchaRitualQuizOptions { skinTypes: TatchaQuizOption[]; benefits: TatchaQuizOption[]; eyeConcerns: TatchaQuizOption[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/tatcha/getRitualQuizOptionsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.tatcha.getRitualQuizOptions();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.tatcha.getRitualQuizOptions())curl -X POST https://api.bowmark.ai/v1/sites/tatcha/getRitualQuizOptions \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.tatcha.getRitualQuizOptions();
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/tatcha/<function> - OpenAPI
/v1/sites/tatcha/openapi.json