57 governed tools, 654 tests, one live MCP server
The falsifiable questionCan one MCP server carry organizational memory, bounded authority, and receipts to every major AI client — and stay up in production?
Baseline and reproducible withheld: the cold-start baseline is argued, not measured, and the server is a product, not a rerunnable harness. The benchmark receipt covers that ground.
Baseline
Without a continuity layer, each AI client starts cold: the goal, prior decisions, quality bar, and permissions live in the human's head and get re-typed into every session. The human is the API between their own tools.
Method
A Cloudflare Worker MCP server (orgx-mcp) exposing 57 tools across memory, planning, delegation, decisions, receipts, and lifecycle — with OAuth, session isolation, and durable state. Distribution manifests shipped for Smithery, Glama, and the ChatGPT apps directory. Test suite: 654 automated cases across ~90 spec files.
Measured result
Live at mcp.useorgx.com with a public .well-known/mcp.json manifest. 57 published tools and 654 passing tests. On July 27, 2026, Smithery independently reported 3,683 tool calls, 99.87% 30-day uptime, and a 95/100 listing score. The longer-window OrgX status page shows 98.283% uptime since April — the incidents remain on the record.
Where it broke
Smithery's platform-reported call count proves traffic reached the server through its registry surface, not retention, customer outcomes, or revenue. The longer-window 98.283% uptime is not 99.9%, real outages sit on the public status page, and GitHub star counts remain near zero.
Updates
- Published to the ledger.
- Added Smithery's external call, uptime, and listing-score evidence; retained the longer-window outage record.
Next test
Bind external calls to retained users and independently verified customer outcomes without exposing private traffic.