For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.mcpbundles.com/bundle/posthog
Skill page: https://www.mcpbundles.com/skills/posthog
Tools: 48
Live probe refreshed Nov 11, 2026 · Endpoint host mcp.mcpbundles.com
AI Skill
SKILL.md
Domain knowledge for PostHog — workflow patterns, data models, and gotchas for your AI agent.
PostHog
PostHog organizes everything under Organizations → Projects. Most API calls are project-scoped, and the default project is auto-selected. Only switch organization or project if the user explicitly asks.
Data Model
Events are the atomic unit — every pageview, click, or custom action is an event with properties.
Event Definitions describe what events exist. Always discover available events before writing queries.
Properties are metadata on events (event type) or users (person type). Discover them before filtering or breaking down.
Insights are saved queries — trends, funnels, retention, paths. Query an existing insight rather than rebuilding it from scratch.
Dashboards are collections of insights arranged as tiles.
Feature Flags control rollouts with percentage-based or property-based targeting. They can be boolean or multivariate.
Experiments are A/B tests tied to feature flags. Each experiment has a linked flag, variants, and success metrics.
Surveys are in-app popover or API-based questionnaires with targeting and scheduling.
Session Recordings capture user sessions as rrweb replay data. Retrieving snapshot data is a two-step process: first get blob keys, then fetch blob content.
Gotchas
$pathname vs $current_url: For URL breakdowns, use $pathname (normalized path) instead of $current_url (includes query params) for cleaner results.
Breakdown limits: Default breakdown limit is 25 values. Set breakdown_limit to 100+ to see more.
Session snapshots are two-step: First request with only session_id to obtain blob keys, then repeat with source, start_blob_key, and end_blob_key to retrieve snapshot bytes.
Experiment results vs experiment details: The experiment object doesn't include statistical results. Fetch the dedicated experiment-results payload when you need outcomes.
Feature flag deletion is permanent: Cannot be undone. Prefer disabling (set inactive) over deleting.
Insight creation: Always execute an insight query in draft before saving it as an insight. Don't save untested query definitions.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms
PostHog
Add to your AI client, then sign in once when you connect.
PostHog is an open-source product analytics platform for tracking events, feature flags, experiments, session recordings, and user behavior.
This listing identifies a third-party integration. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
Posthog Add Insight To Dashboard — Add an existing insight to a dashboard. Requires insight ID and dashboard ID. Optionally supports layout and color customization.
Posthog Bulk Delete Persons — Bulk delete PostHog persons for privacy/GDPR requests. Accepts distinct IDs and/or PostHog person UUIDs, and can queue deletion of historical events and session recordings. Requires a PostHog Personal API Key with person:write.
Posthog Create Dashboard — Create a new dashboard in the project. Requires name and optional description, tags, and other properties.
Posthog Create Experiment — Create a full A/B test experiment. PROCESS: 1) Understand experiment goal and hypothesis 2) Search existing feature flags first 3) Help user define success metrics 4) List event definitions to find available events 5) Configure variants 6) Set targeting criteria.
Posthog Create Feature Flag — Creates a new feature flag in the project. After creation, ask whether the user wants it wired into their codebase; search PostHog documentation for the right language or framework, clarify where it belongs, then add it.
Posthog Create Insight — Create an insight from a query you have already executed successfully. Run the analytics query first and confirm results before saving an insight, unless you already know the query is correct.
Posthog Create Survey — Creates a new survey in the project. Surveys can be popover or API-based and support various question types including open-ended, multiple choice, rating, and link questions. Once created, you should ask the user if they want to add the survey to their application code.
Posthog Delete Dashboard — Delete a dashboard by ID (soft delete - marks as deleted).
Frequently Asked Questions
What is the PostHog MCP server?
PostHog is an open-source product analytics platform for tracking events, feature flags, experiments, session recordings, and user behavior. It provides 48 tools that AI agents can use through the Model Context Protocol (MCP).
How do I connect PostHog to my AI agent?
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/posthog. Authentication is handled automatically.
— Delete an experiment by ID. CAUTION: This action cannot be undone.
Posthog Delete Feature Flag — Delete a feature flag in the project. CAUTION: This action cannot be undone.
Posthog Delete Insight — Delete an insight by ID (soft delete - marks as deleted).
Posthog Delete Survey — Delete a survey by ID (soft delete - marks as archived).
Posthog Generate Hogql — Generate HogQL (SQL) from natural language questions about your analytics data. Use when you need complex event analytics, custom aggregations, or queries that can't be expressed as simple trends/funnels. Slower than the standard analytics query runner but more flexible for ad-hoc analysis of events, users, sessions, pageviews, and custom metrics.
Posthog Get Dashboard — Get a specific dashboard by ID. The response will include insights / tiles that are on the dashboard.
Posthog Get Dashboards — Get all dashboards in the project with optional filtering. Can filter by pinned status, search term, or pagination.
Posthog Get Error Details — Get detailed information about a specific error issue including stack traces, occurrence counts, affected users/sessions, and metadata. Useful for debugging and analyzing specific error patterns.
Posthog Get Experiment — Get details of a specific experiment by ID.
Posthog Get Experiment Results — Get detailed experiment results including all metrics data (primary and secondary) and exposure data. This tool fetches the experiment details and executes the necessary queries to get complete experiment results. Only works with new experiments (not legacy experiments).
Posthog Get Experiments — Get all experiments in the project.
Posthog Get Feature Flag — Get the definition of a feature flag. You can provide either the flag_id or the flag_key. If you provide both, the flag_id will be used.
Posthog Get Feature Flags — Get all feature flags in the project.
Posthog Get Insight — Get a specific insight by ID.
Posthog Get Insights — Get all saved analytics insights (charts, reports, dashboards tiles) in the project. Insights are saved queries showing trends, funnels, retention, paths, and other visualizations. Filter by favorited status or search term.
Posthog Get Llm Costs — Fetches the total LLM daily costs for each model for a project over a given number of days. If no number of days is provided, it defaults to 7. The results are sorted by model name.
Posthog Get Organization Details — Get the details of the active organization.
Showing the first 25 tools — full list and schemas: Directory API.
PostHog provides 48 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.
What authentication does PostHog require?
PostHog uses API Key. PostHog requires credentials. Connect via MCPBundles and authentication is handled automatically.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.
More in analytics
Other MCP servers in this category from the directory index