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.
Why this can grow a startup
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.
Company 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.
Source and metric
Source: PostHog Newsletter · Browse PostHog Newsletter tactics
34% of dashboards created by AI were done through PostHog's MCP server, equal to 18% of all dashboards created that week.
Source discovered: May 26, 2026
When to use it
Use this when AI Search, Developer Tools, Product is relevant to ai products, distribution, demand validation and you can run a bounded test with a medium budget.
When not to use it
Do not use it as a substitute for customer evidence, a clear owner, or a measurable stop condition. Local platform rules and market behavior still need checking.
Founder checklist
- Read PostHog Newsletter and identify what is directly supported.
- Choose one channel context: AI Search, Developer Tools, Product.
- Define the test around 34% of dashboards created by AI were done through PostHog's MCP server, equal to 18% of all dashboards created that week..
- Set an owner, evidence window, and stop condition before launch.
Explore the context
Apply this with an operator
Turn isolated search tactics into a crawlable visibility system tied to demand and proof.