Connect Claude to PostHog's official MCP server for product analytics, feature flags, experiments, dashboards, error tracking, logs, surveys, data warehouse, and project operations.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
63
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
No reviewed flag detected in metadata.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 24/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
No review metadata found; increase manual validation.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Missing required evidence: Metadata review. Risk score 31.
Source repository/provenance is listed.
Required in this preset
Review metadata is missing.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required gaps: Metadata review
Decision timeline
Blocking gaps: Check metadata review status. Risk 28.
triage
Source/provenance metadata is available.
triage
Review metadata is missing.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
Blockers: Check metadata review status
Prerequisite readiness
6 prerequisites to line up before setup. Have accounts and credentials ready first. Includes a review or approval gate.
Safety & privacy surface
7 safety and 5 privacy notes across 6 risk areas. Review closely: credentials & tokens, permissions & scopes, network access.
{
"mcpServers": {
"posthog": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://mcp.posthog.com/mcp?features=docs,insights,error_tracking,events,data_schema",
"--header",
"Authorization:${POSTHOG_AUTH_HEADER}"
],
"env": {
"POSTHOG_AUTH_HEADER": "Bearer phx_your_personal_api_key"
}
}
}
}PostHog MCP Server is PostHog's official Model Context Protocol server for
connecting Claude and other MCP-capable clients to a PostHog project. It is
documented as a hosted endpoint at https://mcp.posthog.com/mcp, with an EU
endpoint at https://mcp-eu.posthog.com/mcp, and the server source lives in
the PostHog monorepo under services/mcp.
The server is useful when a product, growth, support, or engineering workflow needs current PostHog context inside the assistant: recent trends, dashboard state, feature flag configuration, experiment results, error groups, event schemas, logs, LLM analytics, surveys, and project configuration. Because the same MCP surface can also create or change PostHog resources, start with a small feature set and a scoped personal API key.
https://mcp.posthog.com/mcp.https://mcp-eu.posthog.com/mcp.PostHog/posthog under services/mcp.mcp-remote and an Authorization header.features query parameter.tools query parameter.tools mode for one MCP tool per PostHog tool and cli mode for a single
CLI-like wrapper tool.POSTHOG_BASE_URL.PostHog documents feature groups for workspace and project management, actions, activity logs, alerts, annotations, cohorts, dashboards, data schema, data warehouse, docs search, early access features, error tracking, events, experiments, feature flags, CDP functions, insights, LLM analytics, prompts, logs, notebooks, persons, reverse proxy records, search, SQL, surveys, and workflows.
Many tools are read-only, but not all. The source schema marks some tools with write scopes and destructive hints, including deletion, workflow execution, workflow scheduling, feature management, and product-configuration changes.
Use the official PostHog wizard to install the MCP server into supported clients:
npx @posthog/wizard@latest mcp add
The wizard can install into Cursor, Claude, Claude Code, VS Code, and Zed.
Create a personal API key using PostHog's MCP Server preset, then configure a
compatible client with mcp-remote:
{
"mcpServers": {
"posthog": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://mcp.posthog.com/mcp?features=docs,insights,error_tracking,events,data_schema",
"--header",
"Authorization:${POSTHOG_AUTH_HEADER}"
],
"env": {
"POSTHOG_AUTH_HEADER": "Bearer phx_your_personal_api_key"
}
}
}
}
The example above narrows the starting feature set. To expose a different
surface, change the features list or use PostHog's exact tools allowlist:
https://mcp.posthog.com/mcp?tools=dashboard-get,feature-flag-get-all,execute-sql
For EU PostHog projects, use:
https://mcp-eu.posthog.com/mcp
POSTHOG_BASE_URL for self-hosted
PostHog instances.POSTHOG_AUTH_HEADER values.Show that PostHog MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/posthog-mcp-server)PostHog MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
| Field | Connect Claude to PostHog's official MCP server for product analytics, feature flags, experiments, dashboards, error tracking, logs, surveys, data warehouse, and project operations. Open dossier | Manage A/B tests and feature flags in GrowthBook from Claude — list and create experiments, toggle rollouts, review test results, and interact with your GrowthBook workspace — with the official GrowthBook MCP server. Open dossier | Query Mixpanel analytics data from Claude — run insights, funnels, flows, retention analysis, manage dashboards, explore events and properties, run experiments, and analyze session replays — with the official Mixpanel remote MCP server. Open dossier | Create and manage Unleash feature flags from Claude — evaluate whether a change needs a flag, detect existing flags to prevent duplicates, set rollout strategies, toggle environments, and get cleanup guidance — with the official Unleash MCP server following Unleash best practices. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | Not reviewed | Not reviewed | Not reviewed | Not reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed | Source-backed | Source-backed |
| SubmitterDiffers | MkDev11 | — | — | — |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | — | |
| Category | mcp | mcp | mcp | mcp |
| Source | Source-backed | Source-backed | Source-backed | Source-backed |
| Author | PostHog | GrowthBook | Mixpanel | Unleash |
| Added | 2026-06-05 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓The hosted PostHog MCP endpoint is authenticated with a personal API key. Treat that key as a production credential and grant only the read or write scopes needed for the current task. The example configuration uses PostHog's documented `features` query parameter to reduce the exposed tool surface. Feature and tool filtering helps the model choose fewer tools, but API-key scopes remain the real authorization boundary. If no features or tools are specified, PostHog documents that all available tools are exposed. Review the tool list before using an unrestricted endpoint in a production project. Some PostHog MCP tools are mutating or destructive, including tools for creating, updating, archiving, deleting, publishing, enabling, or running product configuration. Keep MCP client approval prompts enabled for those calls. Workflows, alerts, feature flags, experiments, surveys, CDP functions, and data warehouse changes can affect real users, messages, experiments, dashboards, or operational pipelines. Use a development project first. SQL, analytics, error-tracking, log, person, cohort, replay, and data warehouse queries can return large or sensitive result sets. Limit date ranges, filters, and row counts before approving broad queries. Use `https://mcp-eu.posthog.com/mcp` for EU PostHog projects when you need OAuth flows to route to the EU PostHog instance, as documented by PostHog. | ✓`create_experiment` and `create_feature` write to your GrowthBook workspace — capabilities are scoped by your API key/PAT permissions. Creating experiments or feature flags may immediately affect production if they are in a live environment — review before confirming. | ✓The server is hosted by Mixpanel and authenticated via OAuth — your existing Mixpanel project permissions are automatically applied. The MCP server grants read and write access to your Mixpanel project; it can create and modify dashboards, reports, and feature flags. Treat Service Account credentials as secrets; do not commit them to repositories. | ✓`toggle_flag_environment` enables or disables a feature flag in a production environment — confirm before toggling live flags. `create_flag` writes to your Unleash instance; capabilities are scoped by your PAT's permissions. Remote MCP (`--transport http`) is experimental and must be enabled on your Unleash instance. |
| Privacy notes | ✓PostHog MCP can return project metadata, event names, event properties, person and group identifiers, cohorts, feature flag rules, experiment results, dashboards, recordings metadata, errors, logs, warehouse query results, prompts, and LLM analytics data into the model conversation. The MCP server acts as a proxy to your PostHog instance. PostHog documents that queries execute against the connected project and results are returned directly to the AI client, with active project or organization session state cached temporarily using an API-key hash. The hosted server runs on Cloudflare infrastructure. Review PostHog's data processing note, your PostHog region, and your own data-processing agreements before sending regulated customer analytics through an AI client. Do not paste personal API keys, project secrets, raw session recordings, customer identifiers, email addresses, support transcripts, payment data, or exported warehouse rows into prompts or PR comments. Claude transcripts, MCP client logs, screenshots, issue comments, and generated runbooks can retain sensitive PostHog query results outside the access controls and retention settings of the original PostHog project. | ✓Experiment configurations, feature flag definitions, targeting rules, and experiment results from your GrowthBook workspace are surfaced in Claude's context. Your `GB_API_KEY` is a secret — store it as an environment variable, not in version-controlled config files. | ✓Queries and analytics results (event data, user properties, funnel metrics) are sent through Mixpanel's hosted MCP infrastructure. Session replay summaries and user segment data may surface in Claude's context — treat these as sensitive product analytics. | ✓Feature flag names, descriptions, targeting rules, rollout configurations, and project metadata from your Unleash instance are surfaced in Claude's context. Your `UNLEASH_PAT` is a secret — store it as an environment variable and do not commit it to version control. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Official GrowthBook MCP: A/B experiments, feature flags & results from Claude.
Source-backed guides for putting this to work.
Audit MCP client configuration before sharing it with a team.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.