Zentrik
Product context for AI agents: customer evidence, decisions, feature map, and the reasoning behind them. Zentrik MCP exposes a product workspace to an agent. Rather than pasting a spec into a prompt, an agent can query what the team already knows: which customer problems recur, which accounts they affect, what has been decided and why, and how the product is structured. Writes work the same way, so an agent can file a signal, create an idea, or update an initiative. Read: signals and their source evidence, insights, opportunities, ideas, initiatives and specs, the product feature map, product rules, and decision history. Write: create signals from text, create and update ideas and initiatives, attach evidence, answer open questions. Tested with Claude Code, Claude Desktop, Codex, and Cursor. Also listed in the Official MCP Registry as ai.zentrik/mcp and in the Claude Connectors Directory.
First seen 2 Oct 2026. Evidence as of 5 Oct 2026.
Tools
No tool list captured yet.
Change history
No changes since the first observation. The first snapshot is the baseline.
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Smithery | zentrik/product-context | 2 Oct 2026 | 5 Oct 2026 | 1 |