Dome Systems
Dashboard
DocsLearnHands-on LabsTemplatesHelpChangelogCLIAPIMCPSDKs

Ask questions about PostHog

A managed agent for read-only PostHog analytics through OAuth.

User
Caller
  • chat
App
Agent
  • posthog-answerer
Governance
Gateway
  • posthog-analytics
Pool

posthog-answerer-pool

  • posthog-answerer-model
Tools

posthog

    What this template gives you

    • Interface

      A chat window, in your browser

      Use the included interface to send a request to this template.

    • Gateway

      posthog-analytics gateway

      This template sends its requests through posthog-analytics gateway, where its access rules and limits apply.

    • Model

      posthog-answerer-model

      This template uses posthog-answerer-model through the posthog-answerer-pool pool.

    Usage

    Hand this template to an AI agent to set up this template

    Node.js and npm to run npx.

    Dome CLI, installed with brew install dome-systems/tap/dome, then signed in with dome auth login.

    Docker Compose to run the companion app locally.

    1. 1

      Create a workspace

      dome workspaces create --name <workspace-name>

      The CLI creates and selects a workspace context for you.

    2. 2

      Confirm the workspace context

      dome context list

      The workspace you just created is already selected.

    3. 3

      Pull the template

      npx @domesystems/templates pull dome-systems/ai-agent-for-posthog@0.1.0 --dir ai-agent-for-posthog

      Downloads this immutable release and verifies its digest.

    4. 4

      Run the template

      npx @domesystems/templates up --dir ai-agent-for-posthog

      Imports it into Dome and starts the companion app.

    Dome import variables

    npx @domesystems/templates up imports the template into Dome and prompts for required values. For unattended runs, set them as DOME_IMPORT_VAR_… environment variables.

    Required values

    • DOME_IMPORT_VAR_anthropic_api_key

    Setup guide

    Follow this template's setup guidance for agent variables and upstream connections.

    # Configure PostHog

PostHog's hosted MCP server supports OAuth. This template uses the upstream
`readonly=true` option, which removes write MCP tools from the session.

- `anthropic_api_key`: enter the Anthropic key used by this agent's model.
- After import, complete shared OAuth as a dedicated test member and select the
  intended organization and project. Verify a known test insight or event is
  visible and another project is unavailable.

PostHog's MCP exposes a generic `exec` tool, so tool-name filtering alone is
not a complete read-only boundary. Keep the upstream read-only setting, and pin
the connection to one project when production use requires a fixed boundary.
For a headless connection, use a separate personal API key with PostHog's MCP
Server preset instead of modifying this OAuth template.

    Runtime environment

    These variables are required to run the agent. During pull, .env.example is copied to .env when available. If they’re missing, npx @domesystems/templates up retrieves them from Dome and saves them in .env. Pass --provision to refresh them.

    No .env.example is included in this release.

    Agent instructions

    Use PostHog only for analytical, read-only questions. Never create, change, or
delete feature flags, experiments, dashboards, data, people, surveys, or any
other PostHog resource. If a request could change state, refuse it and provide
the read-only analysis or a proposed action instead.