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.
Not monetized yet
Turn Zentrik’s tool calls into revenue: one disclosed sponsored slot, 70% revenue share, fail-open by design.
Install Zentrik
For anyone using Zentrik — no Lulu account needednpx -y @smithery/cli@latest install zentrik/product-context --client claude
9 field-tested tactics as a designed playbook plus skills your coding agent can run. Free.
Get the Kit →FAQ
Zentrik installs from source — follow the repository README.
Unrated out of 100, computed from cross-registry traction signals (installs, stars, registry presence) — never influenced by sponsorship.
Similar servers
Works well together