Test products, prices and ad copy with country-calibrated synthetic consumer panels.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional Folkscale sandbox or live API key. Get a key at folkscale.com/docs.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Generate a census-stratified, psychographically deep national consumer panel.
ISO-2 country code (e.g., US, FI, UK, DE, JP)
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http folkscale https://mcp.folkscale.com/mcp
Headers
X-API-Key (optional, not in the config above): Optional Folkscale sandbox or live API key. Get a key at folkscale.com/docs.Generate a census-stratified, psychographically deep national consumer panel.
| Argument | Type | Description |
|---|---|---|
| size | integer | |
| countryCode* | string | ISO-2 country code (e.g., US, FI, UK, DE, JP) |
{
"type": "object",
"required": [
"countryCode"
],
"properties": {
"size": {
"type": "integer",
"default": 50,
"maximum": 200,
"minimum": 6
},
"countryCode": {
"type": "string",
"description": "ISO-2 country code (e.g., US, FI, UK, DE, JP)"
}
}
}Compute deterministic study pricing and compute estimate before running a study.
| Argument | Type | Description |
|---|---|---|
| modelIds | array | |
| panelSize* | integer | |
| conceptCount* | integer |
{
"type": "object",
"required": [
"panelSize",
"conceptCount"
],
"properties": {
"modelIds": {
"type": "array",
"items": {
"type": "string"
}
},
"panelSize": {
"type": "integer"
},
"conceptCount": {
"type": "integer"
}
}
}Fetch a completed study by ID, optionally recomputed at custom T and epsilon.
| Argument | Type | Description |
|---|---|---|
| epsilon | number | |
| studyId* | string | |
| temperature | number |
{
"type": "object",
"required": [
"studyId"
],
"properties": {
"epsilon": {
"type": "number",
"default": 0
},
"studyId": {
"type": "string"
},
"temperature": {
"type": "number",
"default": 1
}
}
}List available national population blueprints (US, FI, UK, DE, JP, BR, IN + custom).
No arguments.
{
"type": "object",
"properties": {}
}Run a calibrated SSR market study on a panel and return 5-point Likert PMFs, Top-2-Box, subgroup cross-tabs, verbatims, and Executive Brief.
| Argument | Type | Description |
|---|---|---|
| mode | string | |
| title | string | |
| panelId* | string | |
| concepts* | array | |
| scalePresetId | string |
{
"type": "object",
"required": [
"panelId",
"concepts"
],
"properties": {
"mode": {
"enum": [
"sandbox",
"live"
],
"type": "string",
"default": "sandbox"
},
"title": {
"type": "string"
},
"panelId": {
"type": "string"
},
"concepts": {
"type": "array",
"items": {
"type": "object",
"required": [
"title",
"description"
],
"properties": {
"price": {
"type": "string"
},
"title": {
"type": "string"
},
"tagline": {
"type": "string"
},
"description": {
"type": "string"
}
}
}
},
"scalePresetId": {
"type": "string",
"default": "purchase-intent"
}
}
}Project any single consumer quote onto a calibrated 5-point Likert distribution via SSR.
| Argument | Type | Description |
|---|---|---|
| text* | string | |
| scalePresetId | string |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string"
},
"scalePresetId": {
"type": "string",
"default": "purchase-intent"
}
}
}Generate or refresh an Executive Research Brief (verdict, convergent themes, retain list, sharpest criticisms, willingness to pay, singleton insights, actions).
| Argument | Type | Description |
|---|---|---|
| studyId* | string |
{
"type": "object",
"required": [
"studyId"
],
"properties": {
"studyId": {
"type": "string"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.