Zentrik Product Context
About
Connect AI agents to reviewed product context—customer evidence, opportunities, initiatives, decisions, and delivery history—through Zentrik's authenticated MCP server.
Details
- Author
- Unknown
- Categories
- Productivity, Knowledge Base, Other
Jump to
Use Zentrik MCP when you want your assistant to work fromshared product context, not just the contents of the current chat.
The shared values are the same everywhere:
- Server URL:https://zentrik.ai/mcp
- Transport:Streamable HTTPwhen the client asks
- Auth:browser-based OAuth
- Scope:one connection = one workspace
- Open MCP Registry:listed asai.zentrik/mcp
- Claude:listed in the Connectors Directory, so connect it from Claude's connector browser
Start with the guide for the tool you are using:
- Codex setup guide
- Cursor setup guide
- Claude setup guide
- Codexif you want the shortest hosted setup flow
- Cursorif you want Zentrik context available inside your editor and agent workflows
- Claudeif you want product context while researching, synthesizing, or drafting
If you are in another MCP client, use the same server URL and OAuth flow. If the client only asks for a static bearer token or API key, it is not using the right auth flow for Zentrik MCP.
Start with small, evidence-seeking requests:
- ask what Zentrik already knows about a problem, request, or idea
- pull the relevant opportunity, idea, or context record before you plan or build
- add fresh notes from a call, interview, or demo without leaving your current tool
- run a Study learning loop: find or create a private plan, revise it, monitor de-identified evidence, and generate draft findings while keeping launch and participant distribution in Zentrik
- review and answer Idea planning questions, maintain Idea taxonomy and Initiative links, and regenerate generated Initiative documents after approved source changes
- ask what a person or agent changed, with confirmed, no-change, or unverifiable outcomes and explicit coverage
- access is tied to theworkspaceyou approved
- your role in that workspace still matters
- if you want a different workspace, reconnect and choose it
- if newly released tools do not appear, reconnect and approve the current permissions; some clients keep the original grant until you do
- workspace API keys still work for/external/v1, but not for/mcp
- every MCP write creates a durable receipt; the same shared boundary covers product writes reused by Zentrik agents
- usesystem.get_change_historyfor product changes andsystem.get_activityfor background jobs
- change history states whether the requested time and channels are complete, partial, or untracked and summarizes repeated attempts so retry noise does not hide other outcomes
- MCP and Slack-agent product mutations are fully tracked after receipt collection begins; workspace-agent history is partial; UI, External API, integration, background-job, and portal mutations are untracked
- Product management MCP servers comparedfor a dated, source-linked view of Zentrik, Productboard, Aha!, Linear, Atlassian, PostHog, and LaunchDarkly
- Product-to-spec use casefor how signal becomes build-ready scope
- Codex handoff use casefor implementation-ready context
- Claude Code handoff use casefor clearer requirements prompts
- MCP use casesfor practical first prompts
- MCP best practicesfor lighter prompting and realistic limits
Update the client configuration to use OAuth discovery. Legacy workspace API keys are still valid for/external/v1, but they are rejected on/mcp.
Wait a few seconds for the client to finish discovery metadata checks. If it still does not appear, reopen the client and check that the server URL is exactlyhttps://zentrik.ai/mcp.
The token is valid, but it is missing at least one MCP tool scope needed for the current request. Re-run authorization and request the scopes listed in theWWW-Authenticatechallenge.
I authenticated into the wrong workspace
Run the OAuth flow again and choose the correct workspace. Zentrik MCP access tokens are bound to one workspace at a time.
Your response helps us prioritize missing or unclear documentation.
Send your question to Zentrik support. This guide will be included automatically.
Personal Knowledge Base MCP — 22 tools for AI agents to access your curated reading intelligence.
Give your AI assistant the ability to identify cognitive blind spots. The official Model Context Protocol (MCP) server for cognitivebiaslabs.com.
A cognitive framework selector to help choose the right mental models and thinking frameworks for any situation.
An MCP server for advanced cognitive analysis, creative problem-solving, and structured thinking using the UCPF framework.
Search, cite, and read PDFs from your EndNote reference library directly in Claude Desktop
An MCP server implementation that provides a tool for problem-solving using the Lotus Sutra's wisdom framework, combining analytical thinking with intuitive wisdom.
A private, local research "second brain" for Claude — cited answers from your own library (it won't invent what it can't find), persistent project memory, daily briefs, a live meeting assistant, and 34 specialist agents. Runs entirely on your machine.
Let your CLI agents (Claude, Cursor, Codex...) chat directly with NotebookLM for zero-hallucination answers based on your own notebooks
Check workplace safety compliance against OSHA General Industry standards (29 CFR 1910) with cited regulation sections and corrective actions.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
