Developers
One MCP endpoint. Claude, ChatGPT, Claude Code, or any MCP client.
Nazr exposes a Model Context Protocol endpoint at https://app.nazr.com/mcp. A connected agent pulls real tasks with full context, reports what it shipped, and raises signals when the world disagrees with the plan. It can never change the plan directly — every proposed change lands in your review queue, and only humans accept.
https://app.nazr.com/mcp as the URL — no keys needed.Then try: "What should we work on next?" — or after a good strategy conversation, "Send this conversation's decisions to my roadmap as signals." Claude distills the decisions; each arrives in your review queue with provenance.
claude mcp add --transport http nazr https://app.nazr.com/mcpClaude Code walks the same OAuth consent in your browser. For headless or CI use, create an API key in Nazr under Integrations → Your agent and pass it instead:
claude mcp add --transport http nazr https://app.nazr.com/mcp --header "Authorization: Bearer nazr_…"https://app.nazr.com/mcp and OAuth authentication.The endpoint speaks Streamable HTTP with OAuth 2.1 (dynamic client registration, PKCE) or Authorization: Bearer API keys. Discovery metadata lives at https://app.nazr.com/.well-known/oauth-protected-resource/mcp.
| Tool | Access | What it does |
|---|---|---|
get_plan | Read | The full plan tree with statuses and reconcile state |
next_task | Read | The highest-leverage startable task, as a complete brief |
get_task | Read | One task's brief by id |
start_task | Write | Mark a task in progress |
complete_task | Write | Report completion — summary, steps, artifact links |
block_task | Write | Report a blocker with the reason |
raise_signal | Write | Send an observation or decision to the review queue |
get_ground_truth | Read | The org's ground-truth fact ledger |
record_ground_truth | Write | Record or supersede a durable fact |