Mixpanel

SSE

by dragonkhoi

17 340 downloads Not rated yet MIT

GitHub Website

About

Integrates with Mixpanel's API to enable querying of events data, retention, and funnels for on-demand analytics and custom report generation.

Details

Repository: dragonkhoi/mixpanel-mcp
Transport: SSE
License: MIT

Explore

- Query Mixpanel events, retention, and funnel data.
- Works with any MCP client (Cursor, Claude Desktop).
- On-demand natural language analytics lookups.
- Easy installation via Smithery or local clone.
- Authenticates using Mixpanel Service Accounts.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Mixpanel

Command (node, npx, python, etc.) node
Arguments
- Argument 1 /ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js
- Argument 2 YOUR_SERVICE_ACCOUNT_USERNAME
- Argument 3 YOUR_SERVICE_ACCT_PASSWORD
- Argument 4 YOUR_MIXPANEL_PROJECT_ID
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/c",
                "node",
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/c",
                "node",
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/c",
                "node",
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/c",
                "node",
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/c",
                "node",
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

From the repository

Make sure to go to your Mixpanel Organization Settings to set up a Mixpanel Service Account, get the username, password, and your project ID (in Mixpanel Project Settings).

To install mixpanel-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @dragonkhoi/mixpanel-mcp --client claude

To install mixpanel-mcp for Cursor, go to Settings -> Cursor Settings -> Features -> MCP Servers -> + Add

Select Type: command and paste the below, using the arguments <USERNAME> <PW> <PROJECT_ID> from Mixpanel

npx -y @smithery/cli@latest run @dragonkhoi/mixpanel-mcp --config "{\"username\":\"YOUR_SERVICE_ACCT_USERNAME\",\"password\":\"YOUR_SERVICE_ACCT_PASSWORD\",\"projectId\":\"YOUR_MIXPANEL_PROJECT_ID\"}"

`get_today_top_events`

Get today's top events from Mixpanel. Useful for quickly identifying the most active events happening today, spotting trends, and monitoring real-time user activity.

`profile_event_activity`

Get data for a profile's event activity. Useful for understanding individual user journeys, troubleshooting user-specific issues, and analyzing behavior patterns of specific users.

`get_top_events`

Get a list of the most common events over the last 31 days. Useful for identifying key user actions, prioritizing feature development, and understanding overall platform usage patterns.

`aggregate_event_counts`

Get unique, general, or average data for a set of events over N days, weeks, or months. Useful for trend analysis, comparing event performance over time, and creating time-series visualizations.

`aggregated_event_property_values`

Get unique, general, or average data for a single event and property over days, weeks, or months. Useful for analyzing how specific properties affect event performance, segmenting users, and identifying valuable user attributes.

`query_insights_report`

Get data from your Insights reports. Useful for accessing saved analyses, sharing standardized metrics across teams, and retrieving complex pre-configured visualizations.

`query_funnel_report`

Get data for a funnel based on a funnel_id. Useful for analyzing user conversion paths, identifying drop-off points in user journeys, and optimizing multi-step processes. Funnel IDs should be retrieved using the list_saved_funnels tool.

`list_saved_funnels`

Get the names and IDs of your saved funnels. Useful for discovering available funnels for analysis and retrieving funnel IDs needed for the query_funnel_report tool.

`list_saved_cohorts`

Get all cohorts in a given project. Useful for discovering user segments, planning targeted analyses, and retrieving cohort IDs for filtering in other reports.

`query_retention_report`

Get data from your Retention reports. Useful for analyzing user engagement over time, measuring product stickiness, and understanding how well your product retains users after specific actions. Only use params interval or unit, not both.

`custom_jql`

Run a custom JQL (JSON Query Language) script against your Mixpanel data. Useful for complex custom analyses, advanced data transformations, and queries that can't be handled by standard report types.

`query_segmentation_sum`

Sum a numeric expression for events over time. Useful for calculating revenue metrics, aggregating quantitative values, and tracking cumulative totals across different time periods.

`query_profiles`

Query Mixpanel user profiles with filtering options. Useful for retrieving detailed user profiles, filtering by specific properties, and analyzing user behavior across different dimensions.

`query_frequency_report`

Get data for frequency of actions over time. Useful for analyzing how often users perform specific actions, identifying patterns of behavior, and tracking user engagement over time.

`query_segmentation_report`

Get data for an event, segmented and filtered by properties. Useful for breaking down event data by user attributes, comparing performance across segments, and identifying which user groups perform specific actions.

`query_segmentation_bucket`

Get data for an event, segmented and filtered by properties, with values placed into numeric buckets. Useful for analyzing distributions of numeric values, creating histograms, and understanding the range of quantitative metrics.

`query_segmentation_average`

Averages an expression for events per unit time. Useful for calculating average values like purchase amounts, session durations, or any numeric metric, and tracking how these averages change over time.

`top_event_properties`

Get the top property names for an event. Useful for discovering which properties are most commonly associated with an event, prioritizing which dimensions to analyze, and understanding event structure.

`top_event_property_values`

Get the top values for a property. Useful for understanding the distribution of values for a specific property, identifying the most common categories or segments, and planning further targeted analyses.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mixpanel": {
            "env": {},
            "args": [
                "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
                "YOUR_SERVICE_ACCOUNT_USERNAME",
                "YOUR_SERVICE_ACCT_PASSWORD",
                "YOUR_MIXPANEL_PROJECT_ID"
            ],
            "command": "node"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
        "YOUR_SERVICE_ACCOUNT_USERNAME",
        "YOUR_SERVICE_ACCT_PASSWORD",
        "YOUR_MIXPANEL_PROJECT_ID"
    ],
    "command": "node"
}

Macos

{
    "env": [],
    "args": [
        "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
        "YOUR_SERVICE_ACCOUNT_USERNAME",
        "YOUR_SERVICE_ACCT_PASSWORD",
        "YOUR_MIXPANEL_PROJECT_ID"
    ],
    "command": "node"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "node",
        "/ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js",
        "YOUR_SERVICE_ACCOUNT_USERNAME",
        "YOUR_SERVICE_ACCT_PASSWORD",
        "YOUR_MIXPANEL_PROJECT_ID"
    ],
    "command": "cmd"
}

Simple MCP server that interfaces with the Mixpanel API, allowing you to talk to your Mixpanel events data from any MCP client like Cursor or Claude Desktop. Query events data, retention, and funnels. Great for on-demand look ups like: "What's the weekly retention for users in the Feb 1 cohort?"

I am adding more coverage of the Mixpanel API over time, let me know which tools you need or just open a PR.

Installation

Make sure to go to your Mixpanel Organization Settings to set up a Mixpanel Service Account, get the username, password, and your project ID (in Mixpanel Project Settings).

Installing via Smithery

To install mixpanel-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @dragonkhoi/mixpanel-mcp --client claude

To install mixpanel-mcp for Cursor, go to Settings -> Cursor Settings -> Features -> MCP Servers -> + Add

Select Type: command and paste the below, using the arguments <USERNAME> <PW> <PROJECT_ID> from Mixpanel

npx -y @smithery/cli@latest run @dragonkhoi/mixpanel-mcp --config "{\"username\":\"YOUR_SERVICE_ACCT_USERNAME\",\"password\":\"YOUR_SERVICE_ACCT_PASSWORD\",\"projectId\":\"YOUR_MIXPANEL_PROJECT_ID\"}"

Clone and run locally

Clone this repo Run npm run build Paste this command into Cursor (or whatever MCP Client)

node /ABSOLUTE/PATH/TO/mixpanel-mcp/build/index.js YOUR_SERVICE_ACCOUNT_USERNAME YOUR_SERVICE_ACCOUNT_PASSWORD YOUR_PROJECT_ID

Examples

- Ask about retention numbers

- Ask for an overview of events

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

get_today_top_events

profile_event_activity

get_top_events

aggregate_event_counts

aggregated_event_property_values

query_insights_report

query_funnel_report

list_saved_funnels

list_saved_cohorts

query_retention_report

custom_jql

query_segmentation_sum

query_profiles

query_frequency_report

query_segmentation_report

query_segmentation_bucket

query_segmentation_average

top_event_properties

top_event_property_values

Claude Desktop / Cursor

Linux

Macos

Windows

Installation

Installing via Smithery

Clone and run locally

Examples

More like this

Sentry

Github

Brave Search

Git

`get_today_top_events`

`profile_event_activity`

`get_top_events`

`aggregate_event_counts`

`aggregated_event_property_values`

`query_insights_report`

`query_funnel_report`

`list_saved_funnels`

`list_saved_cohorts`

`query_retention_report`

`custom_jql`

`query_segmentation_sum`

`query_profiles`

`query_frequency_report`

`query_segmentation_report`

`query_segmentation_bucket`

`query_segmentation_average`

`top_event_properties`

`top_event_property_values`