Agent work-stack deals page + query helpers (smoke test)
Agent work-stack deals page + query helpers (smoke test)
active Production-safe Score 84/100 http no auth
At a glance
| Endpoint | https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=github-readme |
|---|---|
| Source | https://github.com/connormatthewdouglas/agent-work-stack-deals |
| Transport | http |
| Tools | 13 |
| Auth | none |
| First seen | 2026-11-02 00:19:36 |
| Last checked | 2026-11-17 21:58:49 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 1634 / 2780 ms |
| Last successful check | 2026-11-17 21:58:49 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (13)
compare_gpu_prices— Compare tracked GPU rental prices for one model (e.g. 'H100', 'A100 SXM', 'RTX 4090', 'L40S'), cheapest first. If a result looks wrong, giveget_price_changes— GPU rental price changes among tracked providers, each with old/new hourly price, change_pct, direction, the vendor source_url, a stable eveoptimize_stack— Cheapest suitable stack among tracked providers for monthly needs (set the quantities you need, rest 0). scrape_pages: pages/month withoutoptimize_agent_stack— Estimate a monthly stack cost from a short description of the agent being built. description: free text, e.g. 'scrapes 20k JS pages/month vestimate_job_cost— Cost of one GPU job (not cost per hour) among tracked providers, cheapest current compute subtotal first. gpu_family (e.g. 'H100', 'A100 80rebuild_quote— Reopen a past quote. Pass the `receipt` object returned by optimize_stack, optimize_agent_stack or estimate_job_cost. Returns receipt_intactsearch_deals— Search agent work-stack deals (compute, search, email, unblock, hosting...). offer_type: verified_discount | listed_discount (not confirmedcompare_deals— Compare 2-5 deals side by side (price, unit, offer type, code, verification), best value first.get_deal— Get one deal's public record by id, including redeem_url and agent_instructions.create_watch_key— Hosted only, free, opt-in. Register a webhook for GPU price alerts and get an api_key plus a webhook signing secret (both shown ONCE; storewatch_price— Hosted only. Alert your webhook (signed POST) after the daily refresh when a tracked rate for `gpu` crosses at or below max_hourly_usd, or alist_watches— Hosted only. Your watches and per-key alert counts.delete_watch— Hosted only. Delete one of your watches by watch_id.
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:58:49 | ✓ | ✓ | 1732 ms | 85 | active |
| 2026-11-17 21:43:46 | ✓ | ✓ | 1901 ms | 85 | active |
| 2026-11-17 21:28:41 | ✓ | ✓ | 2923 ms | 85 | active |
| 2026-11-17 21:13:38 | ✓ | ✓ | 920 ms | 89 | active |
| 2026-11-17 20:58:37 | ✓ | ✓ | 1957 ms | 85 | active |
| 2026-11-17 20:43:35 | ✓ | ✓ | 838 ms | 89 | active |
| 2026-11-17 20:28:34 | ✓ | ✓ | 1790 ms | 85 | active |
| 2026-11-17 20:13:32 | ✓ | ✓ | 2025 ms | 85 | active |
| 2026-11-17 19:58:30 | ✓ | ✓ | 1362 ms | 85 | active |
| 2026-11-17 19:43:28 | ✓ | ✓ | 743 ms | 89 | active |
| 2026-11-17 19:28:27 | ✓ | ✓ | 3766 ms | 85 | active |
| 2026-11-17 19:13:23 | ✓ | ✓ | 2438 ms | 85 | active |
| 2026-11-17 18:58:21 | ✓ | ✓ | 2191 ms | 85 | active |
| 2026-11-17 18:43:19 | ✓ | ✓ | 1757 ms | 85 | active |
| 2026-11-17 18:28:17 | ✓ | ✓ | 1136 ms | 85 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=github-readme") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/lantern-works-mcp-lantern-works-workers-dev-mcp-ref-github-readme # JSON