PostHog tools in Cogny
Cogny's PostHog integration exposes 13 tools (13 read) to an AI agent over MCP. The same tools are available on every plan, from your own AI client or inside the Cogny app.
- Read (13): only reads data.
- Write (0): creates or changes something.
- Destructive (0): deletes, removes or replaces something.
Over MCP your own AI client asks before it runs a write. To take a tool away from your agent, block it in Settings → Integrations. Plans, approvals and limits.
All tools
| Tool | Kind | What it does |
|---|---|---|
get_current_user | Read | Get the current user profile. |
list_projects | Read | List all PostHog projects (teams) the API key can access. |
list_insights | Read | List saved insights (charts, funnels, retention etc.) in a project. |
get_insight | Read | Get a single saved insight including its result data. |
list_dashboards | Read | List dashboards in a project. |
list_events | Read | List recent events for a project with optional filters. |
list_event_definitions | Read | List event definitions (names) captured in the project. |
list_property_definitions | Read | List property definitions (event or person properties) for a project. |
list_persons | Read | List persons (user profiles) in a project. |
get_person | Read | Get a single person's profile and all their properties. |
list_cohorts | Read | List cohort definitions in a project. |
list_session_recordings | Read | List session recording metadata for a project. |
list_feature_flags | Read | List feature flag definitions in a project. |
Exact input schemas come from tools/list once PostHog is connected; the free plan is enough to check. Missing something? Your agent can ask for it with request_feature.