PostHog
Capture analytics events and query persons, cohorts, feature flags, insights and annotations via PostHog
About
PostHog ships in the w6w first-party pack. It declares 8 actions, 1 health check, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.posthog- Version
- 0.2.1
- Author
- w6w
- Licence
- MIT
- Categories
- Analytics & BI
Overview
PostHog captures analytics events and reads back a project’s persons, cohorts, feature flags, insights and annotations. Capturing an event uses PostHog’s public, per-project API key and needs no stored connection at all — the same key PostHog ships inside its own frontend snippet — while every other action authenticates against the account-level API with a private personal API key, since reading and writing project data is a different trust level entirely from sending it an event.
Reading persons, cohorts, feature flags and insights, and creating annotations, all scope to one project selected when the connection is made — a single personal API key’s account can span more than one, so the project id is fixed once rather than guessed per call. Annotations can be scoped to a dashboard item, a dashboard, a project or an organization, matching PostHog’s own documented set.
Self-hosted PostHog is not supported; only PostHog’s US and EU cloud regions are reachable, since a fixed egress allowlist can’t address a customer-chosen host.
Build with PostHog
Three routes to the same 8 actions. The Workflow tab is generated from PostHog's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying PostHog's real ids.
{
"manifestVersion": "2",
"name": "posthog-example",
"steps": [
{
"id": "annotation-create",
"uses": {
"app": "io.w6w.posthog",
"action": "annotation-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"content": "<content>"
}
}
]
}Here are some of the things you can do
-
Create Annotation
performannotation-create -
Capture Event
performcapture-event -
List Cohorts
readcohort-list -
Get Feature Flag
readfeature-flag-get -
List Feature Flags
readfeature-flag-list
+3 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for PostHog, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to PostHog. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "capture-event",
payload: {
projectApiKey: "<value>",
region: "<value>",
event: "<value>",
distinctId: "<value>",
// properties: "<value>",
// timestamp: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action capture-event --payload '{"projectApiKey":"<value>","region":"<value>","event":"<value>","distinctId":"<value>"}'Give an AI agent PostHog — without giving it PostHog's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.posthog#annotation-create",
"input": {
"content": "<content>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's PostHog connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
PostHog's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. PostHog itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
PostHog declares its own checks, so its health is a property of the app rather than something the host guesses at.