2,000 years of Greek plant medicine, measured: Dioscorides' Greek → probable spe
2,000 years of Greek plant medicine, measured: Dioscorides' Greek → probable species → compounds → targets → ranked, untested research leads. Website, MCP server, JSON API. Research hypotheses only.
active Production-safe Score 95/100 http no auth
At a glance
| Endpoint | https://pharmakon.adoranto737.workers.dev/mcp |
|---|---|
| Source | https://github.com/LSUDOKO/Pharmakon |
| Transport | http |
| Tools | 6 |
| Auth | none |
| First seen | 2026-11-11 01:05:35 |
| Last checked | 2026-11-17 22:00:37 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 315 / 488 ms |
| Last successful check | 2026-11-17 22:00:37 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (6)
search_ancient_names— Search the ~650 plant and drug names in Dioscorides' De materia medica (1st c.) by Greek (accents optional), transliteration, or modern Latiget_ancient_name— Full record for one ancient name: Greek passages with CTS URNs and verbatim evidence spans, extracted uses, P(species | name) with 90% interlist_leads— Ranked research leads: plant–condition pairs used historically, with no matching PubMed pharmacology paper yet, weighted by identification cget_lead— One lead by rank with its compound → human target → disease evidence paths (LOTUS, ChEMBL, Open Targets) and the exact PubMed query behind ilist_conditions— Conditions that have leads, with counts. Use the names as list_leads condition filters.get_results— Evaluation results with confidence intervals: overview, identification (vs expert gold), persistence (vs permutation null), forecast (rollin
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 22:00:37 | ✓ | ✓ | 330 ms | 90 | active |
| 2026-11-17 21:45:25 | ✓ | ✓ | 275 ms | 94 | active |
| 2026-11-17 21:30:19 | ✓ | ✓ | 386 ms | 90 | active |
| 2026-11-17 21:14:59 | ✓ | ✓ | 369 ms | 90 | active |
| 2026-11-17 20:59:42 | ✓ | ✓ | 477 ms | 90 | active |
| 2026-11-17 20:44:39 | ✓ | ✓ | 401 ms | 90 | active |
| 2026-11-17 20:29:38 | ✓ | ✓ | 424 ms | 90 | active |
| 2026-11-17 20:14:33 | ✓ | ✓ | 529 ms | 90 | active |
| 2026-11-17 19:58:35 | ✓ | ✓ | 344 ms | 91 | active |
| 2026-11-17 19:43:28 | ✓ | ✓ | 292 ms | 94 | active |
| 2026-11-17 19:28:22 | ✓ | ✓ | 524 ms | 91 | active |
| 2026-11-17 19:13:20 | ✓ | ✓ | 221 ms | 94 | active |
| 2026-11-17 18:56:00 | ✓ | ✓ | 257 ms | 94 | active |
| 2026-11-17 18:40:53 | ✓ | ✓ | 190 ms | 94 | active |
| 2026-11-17 18:25:46 | ✓ | ✓ | 437 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://pharmakon.adoranto737.workers.dev/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/pharmakon-adoranto737-workers-dev-mcp # JSON