Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/PostHog/wizardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/posthog/wizard/wizard-ci)<a href="https://agentmods.dev/mcp/posthog/wizard/wizard-ci"><img src="https://agentmods.dev/badge/mcp/posthog/wizard/wizard-ci/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/posthog/wizard/wizard-ci"><img src="https://agentmods.dev/badge/mcp/posthog/wizard/wizard-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
wizard-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"wizard-ci": {
"command": "npx",
"args": [
"tsx",
"scripts/wizard-ci-mcp.no-jest.ts"
]
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 9 lines scan A 291892b78493
wizard-ci is an MCP server published in the GitHub repository PostHog/wizard (197 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
mcp
Official Usertour MCP Server for in-app onboarding: flows, checklists, surveys, and analytics. Remote server at mcp.usertour.io.
posthog-context-mcp
MCP server "posthog-context-mcp" as configured in josephruocco/posthog-mcp-mini. Runs locally from the posthog-context-mcp Python package.
mcp
StepsKit MCP server — author product tours from your codebase through your AI coding agent. Runs locally from the @stepskit/mcp npm package.
survey-mcp-server
MCP server for conducting dynamic, conversational surveys with structured data collection. Runs locally from the @cyanheads/survey-mcp-server npm package. Needs 3 environment variables to run.
posthog-mcp-server
MCP server for PostHog — product analytics for AI assistants. Query events, persons, insights, da... Runs locally from the posthog-mcp-server npm package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.