How do I create a PostHog Personal API Key?

Log in to [**PostHog**](https://app.posthog.com), click your profile icon > **Personal API keys**, then **+ Create a Personal API Key**. Give it a label, select the required scopes and copy the key immediately — it won't be shown again after page refresh.

Can I toggle feature flags via the agent?

Yes! Use `create_feature_flag` to add new flags, `update_feature_flag` to modify existing ones (name, description, enabled status), and `delete_feature_flag` to remove them. You'll need the numeric flag ID from `list_feature_flags` for update and delete operations.

What's the difference between events and persons?

**Events** are actions that happen in your product (pageviews, button clicks, purchases). **Persons** are the users who perform those actions, identified by distinct_id. Events are linked to persons, so you can see what actions a specific user has taken. Use `list_events` to browse activity and `get_person` to see a user's profile.

Can I use this with a self-hosted PostHog instance?

Yes! The tools default to `https://app.posthog.com` for the US cloud, but you can set the `host` parameter to your self-hosted instance URL (e.g. `https://posthog.yourcompany.com`). EU cloud users should set the host to `https://eu.posthog.com`.

PostHog Alternative MCP Server for Google ADK 13 tools — connect in under 2 minutes

Name: PostHog Alternative
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 13 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add PostHog Alternative as an MCP tool provider through the Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token — get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="posthog_alternative_agent",
    instruction=(
        "You help users interact with PostHog Alternative "
        "using 13 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About PostHog Alternative MCP Server

Connect your PostHog account to any AI agent and gain full control over your product analytics, feature flags and user cohorts through natural conversation.

Google ADK natively supports PostHog Alternative as an MCP tool provider — declare the Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 13 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

User & Project Discovery — Verify your account access and list all analytics projects
Feature Flag Management — List, create, update and delete feature flags with rollout configuration
Cohort Inspection — Review all behavioral cohorts and their filter definitions
Person Analytics — Look up individual users by distinct ID, view their properties and activity timeline
Event Tracking — Browse recent events, filter by event type and inspect event properties
Timeline Annotations — Create and review annotations that correlate metric changes with deployments or launches

The PostHog Alternative MCP Server exposes 13 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect PostHog Alternative to Google ADK via MCP

Follow these steps to integrate the PostHog Alternative MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 13 tools from PostHog Alternative via MCP

Why Use Google ADK with the PostHog Alternative MCP Server

Google ADK provides unique advantages when paired with PostHog Alternative through the Model Context Protocol.

Google ADK natively supports MCP tool servers — declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with PostHog Alternative

Production-ready features like session management, evaluation, and deployment come built-in — not bolted on

Seamless integration with Google Cloud services means you can combine PostHog Alternative tools with BigQuery, Vertex AI, and Cloud Functions

PostHog Alternative + Google ADK Use Cases

Practical scenarios where Google ADK combined with the PostHog Alternative MCP Server delivers measurable value.

Enterprise data agents: ADK agents query PostHog Alternative and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine PostHog Alternative tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query PostHog Alternative regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including PostHog Alternative

PostHog Alternative MCP Tools for Google ADK (13)

These 13 tools become available when you connect PostHog Alternative to Google ADK via MCP:

create_annotation

Annotations appear on insights graphs and help correlate metric changes with deployments, launches or incidents. Requires the content text. Optionally set a date_marker (ISO 8601 date). Create a new annotation in PostHog

create_feature_flag

Requires the flag key (unique identifier). Optionally set the name, description, enabled status, rollout percentage and filters. The key must be unique across all flags in the project. Create a new PostHog feature flag

delete_feature_flag

All targeting conditions, release conditions and experiment data associated with the flag will be deleted. Provide the numeric flag ID. WARNING: this action is irreversible. Delete a PostHog feature flag

get_feature_flag

Provide the numeric flag ID from list_feature_flags. Get details for a specific PostHog feature flag

get_person

Provide the distinct_id used to identify the person. Get details for a specific person in PostHog

get_user

Returns user ID, email, name, organization membership and permissions. Use this to verify your API key is working and check your access level. Get the current PostHog user details

list_annotations

Annotations are markers on timeline graphs that highlight important events like deployments, feature launches or incidents. Returns annotation ID, content, date marker and whether it is pinned. List annotations in PostHog

list_cohorts

Each cohort is a dynamic group of users defined by event-based or property-based filters. Returns cohort ID, name, description, whether it is calculated or static. List behavioral cohorts in PostHog

list_events

Optionally filter by event name (e.g. "pageview", "signup", "purchase") and set a limit. Each event includes the event name, timestamp, person distinct ID and properties. List events tracked in PostHog

list_feature_flags

Each flag has a key, name, enabled status, rollout percentage, filters and release conditions. Returns flag ID, key, name, whether it is active, and the targeting configuration. Use this to audit feature flag coverage. List all feature flags in PostHog

list_persons

Each person has distinct IDs, properties, creation date and last event timestamp. Optionally set limit (default 20) and offset for pagination. List persons (users) tracked in PostHog

list_projects

Each project is an analytics workspace with its own events, persons, feature flags and cohorts. Returns project ID, name, organization and creation date. List PostHog projects

update_feature_flag

Provide the flag ID and any fields to change: name, description, enabled status. Only the fields you provide will be updated. Update an existing PostHog feature flag

Example Prompts for PostHog Alternative in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with PostHog Alternative immediately.

"Show me all feature flags and which ones are enabled."

"Create an annotation for today's deployment of version 3.2.0."

"Show me the profile of user 'user_12345'."

Troubleshooting PostHog Alternative MCP Server with Google ADK

Common issues when connecting PostHog Alternative to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

PostHog Alternative + Google ADK FAQ

Common questions about integrating PostHog Alternative MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.