mixpanel
Query Mixpanel events, funnels, retention, segmentation and insights (JQL).
¿Debería usar esto?
Calidad y seguridad
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"mixpanel": {
"url": "https://mixpanel.usefulapi.io/mcp"
}
}
}Puntos de conexión remotos
https://mixpanel.usefulapi.io/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (7)
🟢mixpanel_top_events(type, limit)
List today's top events with counts and % change vs yesterday. Good first call to discover what events a project tracks. Query API: GET /events/top.
Esquema de entrada
{
"type": "object",
"properties": {
"type": {
"description": "general (totals), unique (per-user), or average. Default general.",
"type": "string",
"enum": [
"general",
"unique",
"average"
]
},
"limit": {
"description": "Max events to return. Default 100.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢mixpanel_segmentation(event, from_date, to_date, on, where, ...)
Count/segment/filter a single event over a date range. e.g. 'Signed up' by country last week. Params `on`/`where` use Mixpanel segmentation expressions like properties["$country_code"]. Query API: GET /segmentation. (Upstream maintenance mode — for saved reports prefer mixpanel_query_insights.)
Esquema de entrada
{
"type": "object",
"properties": {
"event": {
"type": "string",
"description": "Single event name to analyze (not an array)."
},
"from_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Start date yyyy-mm-dd (inclusive)."
},
"to_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "End date yyyy-mm-dd (inclusive)."
},
"on": {
"description": "Property expression to segment on, e.g. properties[\"$city\"].",
"type": "string"
},
"where": {
"description": "Filter expression, e.g. properties[\"$os\"]==\"iOS\".",
"type": "string"
},
"unit": {
"description": "Bucket size. Default day.",
"type": "string",
"enum": [
"minute",
"hour",
"day",
"month"
]
},
"type": {
"description": "general | unique | average. Default general.",
"type": "string",
"enum": [
"general",
"unique",
"average"
]
},
"limit": {
"description": "Top N property values (only if `on` set). Default 60.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 10000
}
},
"required": [
"event",
"from_date",
"to_date"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢mixpanel_retention(from_date, to_date, retention_type, born_event, event, ...)
Cohort retention: of users who did `born_event`, how many came back and did `event` over subsequent intervals. Query API: GET /retention.
Esquema de entrada
{
"type": "object",
"properties": {
"from_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Start date yyyy-mm-dd (inclusive)."
},
"to_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "End date yyyy-mm-dd (inclusive)."
},
"retention_type": {
"description": "birth = first-time retention (default), compounded = recurring.",
"type": "string",
"enum": [
"birth",
"compounded"
]
},
"born_event": {
"description": "The defining first event for a birth cohort. Required when retention_type=birth.",
"type": "string"
},
"event": {
"description": "Returning event to measure. If omitted, any event counts.",
"type": "string"
},
"born_where": {
"description": "Filter expression applied to born_event.",
"type": "string"
},
"where": {
"description": "Filter expression applied to the returning event.",
"type": "string"
},
"interval": {
"description": "Units per bucket (<=90 if days). Default 1.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"interval_count": {
"description": "Number of intervals to report.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"unit": {
"description": "Interval unit. Default day.",
"type": "string",
"enum": [
"day",
"week",
"month"
]
}
},
"required": [
"from_date",
"to_date"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢mixpanel_list_funnels
Get the funnel_id and name of every saved funnel in the project. Query API: GET /funnels/list.
Esquema de entrada
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢mixpanel_query_funnel(funnel_id, from_date, to_date, length, length_unit, ...)
Get conversion data for a saved funnel (use mixpanel_list_funnels to find funnel_id). Query API: GET /funnels.
Esquema de entrada
{
"type": "object",
"properties": {
"funnel_id": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "Saved funnel id (from mixpanel_list_funnels)."
},
"from_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Start date yyyy-mm-dd (inclusive)."
},
"to_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "End date yyyy-mm-dd (inclusive)."
},
"length": {
"description": "Conversion window length.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"length_unit": {
"description": "Unit for `length`.",
"type": "string",
"enum": [
"day",
"hour",
"minute",
"second",
"week",
"month"
]
},
"interval": {
"description": "Number of days per bucket.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"unit": {
"description": "Bucketing unit.",
"type": "string",
"enum": [
"day",
"week",
"month"
]
},
"limit": {
"description": "Limit on segmentation breakdown.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"funnel_id",
"from_date",
"to_date"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢mixpanel_query_insights(bookmark_id, workspace_id)
Fetch the computed data behind a saved Insights report by bookmark_id (the report id in the board URL). Mixpanel's recommended, non-deprecated path for programmatic reporting. Query API: GET /insights.
Esquema de entrada
{
"type": "object",
"properties": {
"bookmark_id": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "Insights report id (bookmark_id) from the report URL."
},
"workspace_id": {
"description": "Workspace id, if applicable.",
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
}
},
"required": [
"bookmark_id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢mixpanel_jql(script, params)
Run a custom JQL (JavaScript Query Language) script for arbitrary analysis. Power-user escape hatch. Script must define main(). Query API: POST /jql. (Upstream maintenance mode; 2-min timeout, 5GB/query limit.)
Esquema de entrada
{
"type": "object",
"properties": {
"script": {
"type": "string",
"description": "JQL script defining function main(){ ... } that returns rows."
},
"params": {
"description": "Optional JSON string exposed to the script as the `params` global.",
"type": "string"
}
},
"required": [
"script"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}Comunidad
Evidencia