Cafeteria

Query what Gen Z and Gen Alpha respondents say about brands in Claude.

Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.

Paste it into any MCP client. Setup docs

What the Cafeteria connector does

The Cafeteria MCP server lets brand and research teams ask Claude what young consumers think, answered from Cafeteria's own Gen Z and Gen Alpha survey responses. Its five tools rank the brands people mention, compare named brands by age, gender and state, and run read-only SQL. The only write sends Cafeteria a custom-research request, and only when you ask.

Verified connector

Listed by Anthropic as a partner connector in its Connectors Directory.

Connection checked by Agentman on .

Anthropic states this reflects the level of review a connector received, not a security audit.

Cafeteria tools (5)

  • custom_table_offer
  • mention_count
  • query_cafeteria_tables
  • request_custom_table
  • top_entities

Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.

Limits

  • Cafeteria clients only. The connector needs a Cafeteria account, and answers are limited to the tables your organization is licensed for.
  • Respondents include minors. Cafeteria's participants are aged 14 to 26. Verbatim answers arrive with gender, age and city or state, as Cafeteria's own MCP page shows. Treat quotes as research data about real people, and do not try to identify anyone.
  • Small slices are thin. Filtering by age, gender and state shrinks the respondent count fast; the tools return counts so you can see it.
  • SQL is capped. query_cafeteria_tables returns at most 1,000 rows and is read-only.
  • Pricing is not public. Cafeteria's FAQ says S/NTH is licensed by usage, not seat, and that pricing is scoped per engagement; its MCP page describes a flat subscription. Confirm with Cafeteria.
  • Tool schemas are unverified. We could not read the tool list or annotations without signing in, and we called no tool.

Frequently asked questions

What is a Cafeteria table?

A table is Cafeteria's name for one research session: a focused set of questions on a topic, sent to participants through the Cafeteria app. Cafeteria Tables are always on and shared across all clients. Custom Tables are built for one brand, and Cafeteria says their answers are never shared outside that organization. The connector queries only the tables your organization is licensed for.

Who are the people behind the responses?

They are Cafeteria app participants aged 14 to 26, per Cafeteria's client FAQ. Everyone is invited or accepted from a waitlist, then quality-scored, and Cafeteria removes low-effort respondents. It says it benchmarks the base against U.S. census data by state and ZIP code. Respondents answer by voice note or text, so the connector returns their own words.

How large are the samples behind an answer?

Cafeteria says broad tables exceed 385 responses, the common benchmark for 95% confidence and a 5% margin of error. For narrowly targeted custom studies it works with about 100 responses, which it calls decision-ready. A filtered query in Claude can cut a table well below either number, so check the unique-respondent count each tool returns before quoting a result.

Sources

Use it in an agent

Put Cafeteria to work.

Connect Cafeteria once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.

Call (650) 285-1019, Agentman.Our AI receptionist answers.