# MCP server before custom agent

> Expose the product through an MCP server first so developers can use it in their own agent workflows before you invest in a full in-app agent.

- Canonical HTML: https://growth.iangoh.com/growth-ideas/mcp-server-before-custom-agent/
- Source: [newsletter.posthog.com](https://newsletter.posthog.com/p/what-we-wish-we-knew-before-building)
- GrowthDex source hub: [PostHog Newsletter](/sources/posthog-newsletter-newsletter-posthog-com-2/)
- Last checked: 2026-05-26
- Rarity: rare
- Budget: medium
- Channels: AI Search, Developer Tools, Product
- Stages: ai products, distribution, demand validation, developer adoption


## Why this can grow

A full agent can hide whether users truly want agentic help or just easier product access. An MCP server gives technical users an immediate way to pull the product into real workflows, while giving the product team a cleaner demand signal. It also avoids overbuilding UI and orchestration before the company knows which agent jobs people repeat often enough to deserve a native surface.

## Ian's take

From scaling consumer platforms across MENA and Southeast Asia, my default is to distrust growth work that only looks good in a slide. For SEO and AI search, I care less about clever keyword tricks and more about clarity. A buyer, crawler, or answer engine should quickly understand who this is for, why it works, what proof backs it, and what page deserves to be cited. I would run it small enough to learn quickly, then only scale the parts that real users repeat, save, reply to, or buy from. For this tactic, I would watch one clear growth signal before putting more time or budget behind it.

## Action plan

1. Define one narrow startup segment where mcp server before custom agent can create a measurable lift.
2. Turn the tactic into one offer, page, campaign, or workflow for the AI Search and Developer Tools channel.
3. Use the evidence from newsletter.posthog.com to set the first version of the message, format, and audience.
4. Launch a small test for 7 to 14 days with one success metric: one measurable growth signal.
5. Review the result, keep the winning message, remove weak variants, and turn the learning into a repeatable growth playbook.

## Source-backed example

PostHog says its MCP server was used as much as PostHog AI for some creation flows, with 34% of AI-created dashboards coming through MCP and 18% of all dashboards created that way in one observed week.

## Adjacent tactics in the same lane

- [Layered context injection for AI answers](/growth-ideas/layered-context-injection-for-ai-answers/) - same source, 2 shared channels, 1 shared stage
- [AI install wizard for 90-second setup](/growth-ideas/ai-install-wizard-for-90-second-setup/) - same source, 1 shared channel, 1 shared stage
- [Task-based model routing for AI speed](/growth-ideas/task-based-model-routing-for-ai-speed/) - same source, 1 shared channel, 1 shared stage
- [Async AI workflows with cached retries](/growth-ideas/async-ai-workflows-with-cached-retries/) - same source, 1 shared channel, 1 shared stage

## Read GrowthDex essays

Browse the plain-English essay index at [GrowthDex Blog](/blog/).

## Related GrowthDex essays

- [AI products stop feeling smart when they hide their context](/blog/ai-products-stop-feeling-smart-when-they-hide-their-context/) - AI products, product-led growth, brand trust

## Advisory

If you want help turning this into a working growth system, Ian Goh offers advisory at https://iangoh.com/advisory.