Is this an official PostHog MCP server?

No. It is Memtro's MCP server with Memtro's PostHog connector behind it: the connector reads PostHog through its API with the credentials you connect on Dashboard → Connections, and PostHog publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in PostHog?

Not yet. Today every PostHog tool reads, searches or lists; when it gains actions, each is marked, granted by name and used only when you ask, so nothing is created, sent, updated or deleted until you say so.

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

MCP server · Analytics

PostHog MCP server

PostHog in any MCP client, through Memtro: PostHog does not publish this server. Memtro's PostHog connector reads PostHog through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Read-only PostHog product analytics: HogQL queries over events, persons and sessions, trends, saved insights, person lookups with recent events and session recordings, feature flags, experiments and surveys (PostHog allows 240 analytics requests per minute (1,200 per hour) and 2,400 query requests per hour per organisation.).

Reads

posthog_queryRun a read-only HogQL (ClickHouse-flavoured SQL) query against the project.
posthog_trendsEvent counts over time (a PostHog Trends insight): one or more events, a date range (default -7d → now) and a bucket interval…
posthog_insightsSaved insights (the charts people built in PostHog).
posthog_personFind people by email, name or distinct id and return their person properties, identifiers, first/last seen, plus…
posthog_feature_flagsFeature flags: key, description, enabled, rollout per condition group (percentage and property filters), variants for multivariate flags…
posthog_experimentsA/B experiments and surveys.

Connect it

First connect PostHog on Dashboard → Connections, then add Memtro to your client once. The PostHog tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

One command registers the server; the tools are then available in every session.

claude mcp add --transport http memtro https://platform.memtro.com/api/mcp \
  --header "Authorization: Bearer sk-memtro-..."

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared PostHog connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

› How many unique users viewed pricing each day this week?
› Top 20 events in the last 7 days with counts
› What is the current result of our 'Activation funnel' insight?
› What has jane@acme.com done recently, and are there session recordings?
› Which feature flags are enabled for enterprise customers?
› Is the new-checkout experiment still running and what did it conclude?

Questions

Is this an official PostHog MCP server?: No. It is Memtro's MCP server with Memtro's PostHog connector behind it: the connector reads PostHog through its API with the credentials you connect on Dashboard → Connections, and PostHog publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?: Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in PostHog?: Not yet. Today every PostHog tool reads, searches or lists; when it gains actions, each is marked, granted by name and used only when you ask, so nothing is created, sent, updated or deleted until you say so.
Which clients work?: Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.