/debugging-mcp-analytics
Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the `@posthog/mcp` and `posthog.mcp` SDKs plus the mcp_analytics product). Use when MCP analytics data looks wrong or missing ("events aren't showing", "intent clusters are empty", "sessions are
$ npx -y skills add posthog/posthog --skill debugging-mcp-analytics --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/debugging-mcp-analytics
Context preview
The summary Claude sees to decide when to auto-load this skill.
Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the `@posthog/mcp` and `posthog.mcp` SDKs plus the mcp_analytics product). Use when MCP analytics data looks wrong or missing ("events aren't showing", "intent clusters are empty", "sessions are
SKILL.md
debugging-mcp-analytics.SKILL.mdname: debugging-mcp-analytics
description: >
Debug, support, and build PostHog MCP Analytics — product analytics for MCP
servers (the `@posthog/mcp` and `posthog.mcp` SDKs plus the mcp_analytics
product). Use when MCP analytics data looks wrong or missing ("events aren't
showing", "intent clusters are empty", "sessions are missing", "per-tool
numbers look wrong"), when writing queries over `$mcp_*` events by hand, or
when doing feature work on the SDKs, the dashboard and its query runners, the
self-instrumented MCP server, the `wizard mcp-analytics` install command, or
the in-app onboarding. Covers the repo map, the `$mcp_*` vocabulary and where
each property comes from, the rules that silently corrupt metrics when
ignored, the end-to-end pipeline and where each stage breaks, and which repo
to change. For reading the data rather than fixing it, prefer the
`exploring-mcp-*` and `improving-mcp-tools` skills.Debugging MCP analytics
**Product analytics for MCP servers.** A team ships an MCP server; the `@posthog/mcp` SDK wraps it in one line; every tool call, agent **intent**, and failure lands in PostHog as a `$mcp_*` event you can query, chart, alert on, and cluster — plus a dedicated dashboard. The MCP-layer sibling of `@posthog/ai`.
The differentiator is **intent**: not "ran `query_run` 14 times" but "was trying to find a churn cohort". Explicit non-goal: this does **not** replace LLM analytics / AI observability — generation traces, prompt/response, and token cost belong there.
Status: **beta**, TypeScript and Python SDKs shipped, whole product still behind the `mcp-analytics` early-access flag (`products/mcp_analytics/frontend/featurePreviewGate.ts`). PostHog dogfoods it — its own MCP server instruments itself, and that data drives the dashboard. Public tracking: mega-issue **PostHog/posthog#64016**, which is the live source for roadmap and customer wishlist.
Repos
GitHub is the source of truth for where the code lives. Paths below are in-repo; for the repos outside this monorepo, resolve a local checkout via [references/local-repos.md](references/local-repos.md) rather than assuming a location.
| Concern | Repo | Where to look | | --------------------------------- | ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Product / dashboard** | `PostHog/posthog` (this repo) | `products/mcp_analytics/` — Django/DRF + HogQL query runners + Temporal, Kea frontend, the `query-mcp-*` tool registry, and the analysis skills | | **Self-instrumented server** | `PostHog/posthog` (this repo) | `services/mcp/` — PostHog's own MCP server (Hono); the dogfood event producer. Also hosts the _generated_ `query-mcp-*` handlers | | **Shared query reference** | `PostHog/posthog` (this repo) | `products/posthog_ai/skills/querying-posthog-data/references/models-mcp.md` | | **TypeScript SDK** `@posthog/mcp` | `PostHog/posthog-js` | `packages/mcp/` — the library customers install. Vocabulary source of truth: `src/extensions/constants.ts`. `docs/ARCHITECTURE.md` is stale on the session model (it predates conversation anchoring) — trust `CHANGELOG.md` and the source | | **Python SDK** `posthog.mcp` | `PostHog/posthog-python` | `posthog/mcp/` — mirrors `posthog.ai`. Ships inside `posthog` (`pip install posthog`); `mcp`/`fastmcp` are lazily-imported peer deps, **no `[mcp]` extra** | | **Docs** | `PostHog/posthog.com` | `contents/docs/mcp-analytics/` (incl. `surfaces/`), plus `src/hooks/productData/mcp_analytics.tsx` and the `mcp_analytics` entry in `src/data/tools.ts` | | **Install codemod** | `PostHog/context-mill` | `context/skills/mcp-analytics/{config.yaml,description.md}` | | **Wizard CLI** | `PostHog/wizard` | `bin.ts`, `src/commands/mcp-analytics.ts`, `src/lib/programs/mcp-analytics/` | | **Wizard test harness** | `PostHog/wizard-workbench` | `apps/mcp-analytics/` fixtures |
**Don't conflate:**
- `PostHog/mcp-analytics` is the **archived prototype** of this SDK — stuck at `0.0.9` with an
old `track(server, {...})` API. It published under the same `@posthog/mcp` name, so grepping that name can land you there. npm `@posthog/mcp` now resolves to `PostHog/posthog-js`.
- `products/mcp_store/` is the MCP server marketplace / team gateway, not this product. (Older
notes also mention a `products/mcp
Read more
name: debugging-mcp-analytics
description: >
Debug, support, and build PostHog MCP Analytics — product analytics for MCP
servers (the `@posthog/mcp` and `posthog.mcp` SDKs plus the mcp_analytics
product). Use when MCP analytics data looks wrong or missing ("events aren't
showing", "intent clusters are empty", "sessions are missing", "per-tool
numbers look wrong"), when writing queries over `$mcp_*` events by hand, or
when doing feature work on the SDKs, the dashboard and its query runners, the
self-instrumented MCP server, the `wizard mcp-analytics` install command, or
the in-app onboarding. Covers the repo map, the `$mcp_*` vocabulary and where
each property comes from, the rules that silently corrupt metrics when
ignored, the end-to-end pipeline and where each stage breaks, and which repo
to change. For reading the data rather than fixing it, prefer the
`exploring-mcp-*` and `improving-mcp-tools` skills.Debugging MCP analytics
**Product analytics for MCP servers.** A team ships an MCP server; the `@posthog/mcp` SDK wraps it in one line; every tool call, agent **intent**, and failure lands in PostHog as a `$mcp_*` event you can query, chart, alert on, and cluster — plus a dedicated dashboard. The MCP-layer sibling of `@posthog/ai`.
The differentiator is **intent**: not "ran `query_run` 14 times" but "was trying to find a churn cohort". Explicit non-goal: this does **not** replace LLM analytics / AI observability — generation traces, prompt/response, and token cost belong there.
Status: **beta**, TypeScript and Python SDKs shipped, whole product still behind the `mcp-analytics` early-access flag (`products/mcp_analytics/frontend/featurePreviewGate.ts`). PostHog dogfoods it — its own MCP server instruments itself, and that data drives the dashboard. Public tracking: mega-issue **PostHog/posthog#64016**, which is the live source for roadmap and customer wishlist.
Repos
GitHub is the source of truth for where the code lives. Paths below are in-repo; for the repos outside this monorepo, resolve a local checkout via [references/local-repos.md](references/local-repos.md) rather than assuming a location.
| Concern | Repo | Where to look | | --------------------------------- | ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Product / dashboard** | `PostHog/posthog` (this repo) | `products/mcp_analytics/` — Django/DRF + HogQL query runners + Temporal, Kea frontend, the `query-mcp-*` tool registry, and the analysis skills | | **Self-instrumented server** | `PostHog/posthog` (this repo) | `services/mcp/` — PostHog's own MCP server (Hono); the dogfood event producer. Also hosts the _generated_ `query-mcp-*` handlers | | **Shared query reference** | `PostHog/posthog` (this repo) | `products/posthog_ai/skills/querying-posthog-data/references/models-mcp.md` | | **TypeScript SDK** `@posthog/mcp` | `PostHog/posthog-js` | `packages/mcp/` — the library customers install. Vocabulary source of truth: `src/extensions/constants.ts`. `docs/ARCHITECTURE.md` is stale on the session model (it predates conversation anchoring) — trust `CHANGELOG.md` and the source | | **Python SDK** `posthog.mcp` | `PostHog/posthog-python` | `posthog/mcp/` — mirrors `posthog.ai`. Ships inside `posthog` (`pip install posthog`); `mcp`/`fastmcp` are lazily-imported peer deps, **no `[mcp]` extra** | | **Docs** | `PostHog/posthog.com` | `contents/docs/mcp-analytics/` (incl. `surfaces/`), plus `src/hooks/productData/mcp_analytics.tsx` and the `mcp_analytics` entry in `src/data/tools.ts` | | **Install codemod** | `PostHog/context-mill` | `context/skills/mcp-analytics/{config.yaml,description.md}` | | **Wizard CLI** | `PostHog/wizard` | `bin.ts`, `src/commands/mcp-analytics.ts`, `src/lib/programs/mcp-analytics/` | | **Wizard test harness** | `PostHog/wizard-workbench` | `apps/mcp-analytics/` fixtures |
**Don't conflate:**
- `PostHog/mcp-analytics` is the **archived prototype** of this SDK — stuck at `0.0.9` with an
old `track(server, {...})` API. It published under the same `@posthog/mcp` name, so grepping that name can land you there. npm `@posthog/mcp` now resolves to `PostHog/posthog-js`.
- `products/mcp_store/` is the MCP server marketplace / team gateway, not this product. (Older
notes also mention a `products/mcp
:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
Repo: posthog/posthog
Other skills on posthog.
- /analyzing-expensive-users
Analyze the most expensive users in AI observability and explain why they cost so much. Use when the user asks about top spenders, expensive users, per-user LLM cost, user-level cost drivers, or patterns behind high AI observability spend.
Open skill - /creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously
Open skill - /exploring-ai-failures
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues
Open skill - /exploring-llm-clusters
Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.
Open skill - /exploring-llm-costs
Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?",
Open skill - /exploring-llm-evaluations
Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query individual results, and
Open skill

