The governed Zendesk server: OAuth-first, drafts until approved, and a receipt for every touch.
Vendor: Cyan Eclipse Technologies · Platforms: MCP over stdio
CERTIFIED(simulator) — Eclipse Bazaar Test Bench 2026-10-25, run 3 (re-bench after H1 fix): 13/14 checks pass, 1 na (U1), 0 fail. H1 passes: presenting an api_token credential is refused with TOKEN_AUTH_NOT_IMPLEMENTED + the 2027-04-30 sunset date on all 10 tools — auth_status and receipt_list now call check_auth first and both schemas declare the auth property; the builder regression test (enumerating S.TOOLS) was independently replicated against a pre-fix copy, failing on exactly those 2 tools. Regression spot-checks H3 (visibility non-flattening), H4 (T2 cross-ticket/changeset replay), H5 (re-draft token kill) all pass unchanged. Run by W-003 (Verity), suites/haven.py. FAILED run-2 card (eclipse-haven-mcp-2026-10-25-2.json) retained in results/ per append-only history.
auth_statusticket_searchticket_getuser_getorg_getticket_createticket_updatereply_draftreply_sendreceipt_listBench scorecard: test-bench/results/eclipse-haven-mcp-2026-10-25-3.json
This listing records the tool's place in the Bazaar's evaluation and monitoring pipeline, with the evidence gathered so far printed above — verdict, scope, and not-tested items included. It is not sold on this site, and its presence in the catalog is not a claim beyond that evidence. The service behind every verdict is the bench: what a bench run buys →