Overview

The PostHog MCP Server is an open-source Model Context Protocol (MCP) server that connects AI assistants (like Cline or Cursor) to PostHog’s analytics platform via natural language commands. It enables tasks like creating annotations, managing projects, querying insights, and toggling feature flags—all without touching PostHog’s UI.

Official Server:

Developed and maintained by PostHog

Key Features

📊

Project Management

List and manage PostHog projects

📝

Annotations

Add timestamped notes for events (e.g., product launches)

🚀

Feature Flags

Control and query feature flags dynamically

🐛

Error Tracking

Debug errors directly in your IDE

Available Tools

Quick Reference

Tool	Purpose	Category
`list_projects`	List all PostHog projects	Project Management
`create_annotation`	Create a new annotation	Annotations
`get_feature_flag`	Get the status of a feature flag	Feature Flags
`set_feature_flag`	Set the status of a feature flag	Feature Flags
`get_error_details`	Get details of an error	Error Tracking

Detailed Usage

list_projects▶

List all projects in your PostHog organization.

use_mcp_tool({
  server_name: "posthog",
  tool_name: "list_projects",
  arguments: {}
});

create_annotation▶

Create a new annotation for a specific project.

use_mcp_tool({
  server_name: "posthog",
  tool_name: "create_annotation",
  arguments: {
    project_id: 123,
    content: "Launched new marketing campaign",
    date_from: "2024-01-01T00:00:00Z"
  }
});

get_feature_flag▶

Get the status of a specific feature flag for a project.

use_mcp_tool({
  server_name: "posthog",
  tool_name: "get_feature_flag",
  arguments: {
    project_id: 123,
    flag_key: "new-ui"
  }
});

set_feature_flag▶

Set the status of a specific feature flag for a project.

use_mcp_tool({
  server_name: "posthog",
  tool_name: "set_feature_flag",
  arguments: {
    project_id: 123,
    flag_key: "new-ui",
    enabled: true
  }
});

get_error_details▶

Get details of a specific error for a project.

use_mcp_tool({
  server_name: "posthog",
  tool_name: "get_error_details",
  arguments: {
    project_id: 123,
    error_id: "error-abc-123"
  }
});

Installation

{
  "mcpServers": {
    "posthog": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://mcp.posthog.com/sse",
        "--header",
        "Authorization:${POSTHOG_AUTH_HEADER}"
      ],
      "env": {
        "POSTHOG_AUTH_HEADER": "Bearer {INSERT_YOUR_PERSONAL_API_KEY_HERE}"
      }
    }
  }
}

Custom Connection:

Replace {INSERT_YOUR_PERSONAL_API_KEY_HERE} with your actual PostHog personal API key. If you're using PostHog EU cloud or a self-hosted instance, you can specify a custom base URL by adding the POSTHOG_BASE_URL environment variable.

Common Use Cases

1. Annotate Product Launches

Create annotations for product launches or significant events to correlate with analytics data:

use_mcp_tool({
  server_name: "posthog",
  tool_name: "create_annotation",
  arguments: {
    project_id: 123,
    content: "New feature X launched to all users",
    date_from: "2024-05-20T10:00:00Z"
  }
});

2. Toggle Feature Flags

Programmatically enable or disable feature flags based on certain conditions:

// Enable a feature flag
use_mcp_tool({
  server_name: "posthog",
  tool_name: "set_feature_flag",
  arguments: {
    project_id: 123,
    flag_key: "dark-mode",
    enabled: true
  }
});

// Disable a feature flag
use_mcp_tool({
  server_name: "posthog",
  tool_name: "set_feature_flag",
  arguments: {
    project_id: 123,
    flag_key: "old-dashboard",
    enabled: false
  }
});

3. Monitor Errors

Retrieve details about specific errors to aid in debugging and incident response:

use_mcp_tool({
  server_name: "posthog",
  tool_name: "get_error_details",
  arguments: {
    project_id: 123,
    error_id: "error-404-page-not-found"
  }
});

Connection String Format

The PostHog MCP server primarily uses API keys for authentication. For npx installation, the Authorization header is used. For python installation, the POSTHOG_API_TOKEN environment variable is used.

Sources

Google Analytics MCP Server: AI-Powered Analytics for GA4

Google Analytics MCP server enables AI models to interact with Google Analytics 4 for reports, user behavior analysis, event tracking, and real-time data access.

Airtable MCP Server

Airtable MCP servers enable AI models to interact with Airtable bases, providing capabilities for base management, record operations, field configuration, and structured data automation.

Neon MCP Server

Neon MCP servers enable AI models to interact with serverless PostgreSQL databases, providing capabilities for structured data operations, SQL queries, database branching, and automatic scaling in a fully managed environment.

PostHog MCP Server: AI-Powered Analytics & Feature Flags