Allium MCP

Observed record — 91 daily checks since 2026-07-26

Succeeded

63

Failed

28

Their error

0

Unattributed

28

State changed on 2026-09-25 (responding → unreachable from our probe), 2026-09-26 (unreachable from our probe → responding), 2026-09-28 (responding → unreachable from our probe).

This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 37 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Every one of them passed, so the rate covers them too.

Last 30 days — to 2026-10-24, one point per UTC day

A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.

Tool inventory history — 48 now, peak 48, since 2026-07-26

• 2026-09-23 47 → 48 +1 (search_dashboards)
• 2026-09-21 46 → 47 +25 (get_realtime_crosschain_assets, get_realtime_holdings_history, get_realtime_holdings_pnl, get_realtime_holdings_pnl_by_token…) −24 (realtime_fills, realtime_get_assets, realtime_get_positions, realtime_get_supported_chains…)
• 2026-09-04 48 → 46 −2 (share_dashboard, share_explorer_query)
• 2026-08-12 47 → 48 +1 (list_compute_profiles)
• 2026-08-05 43 → 47 +5 (create_explorer_visual, delete_explorer_visual, get_explorer_visual, get_terminal_results…) −1 (create_explorer_chart)

Recorded from our own daily tools/list handshake. A shrinking toolset is a real signal for an agent choosing a server; a gap in the series means the probe did not succeed that day, not that the tools disappeared.