costable.ai
https://costable.ai/api/mcp
active Production-safe Score 81/100 http no auth
At a glance
| Endpoint | https://costable.ai/api/mcp |
|---|---|
| Source | https://github.com/smart-mcp-proxy/mcpproxy-go/blob/main/internal/registries/testdata/catalog_github_order.json |
| Transport | http |
| Tools | 10 |
| Auth | none |
| First seen | 2026-10-02 18:23:38 |
| Last checked | 2026-11-17 21:50:24 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 2046 / 3895 ms |
| Last successful check | 2026-11-17 21:50:24 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (10)
estimate_part— Instantly estimate the should-cost of a manufactured part using natural language. Returns P50 (median), P80 and P90 cost-at-risk per unit basearch_materials— Search the Costable materials database (37 materials with LME-sourced pricing). Returns material name, category, price per kg, density, andsearch_processes— Search the Costable manufacturing process database (41 processes). Returns process name, category, machine rate ($/hr), and cycle time modelget_labour_rates— Get manufacturing labour rates ($/hr) for all skill levels in a given country. Data covers 16 skill levels across 25 countries (ILO/BLS/ABScreate_cost_model— Create a new parametric cost model in Costable. Returns the model ID which is used by add_material_to_model, add_process_to_model, calculateadd_material_to_model— Add a material (BOM line) to an existing cost model. Searches the materials database by name query — no need for exact IDs.add_process_to_model— Add a manufacturing process step to an existing cost model. Searches the process database by name query — no need for exact IDs.calculate_cost_model— Run the Monte Carlo should-cost calculation on a cost model. Returns P50 (median), P80 and P90 cost-at-risk per unit, plus a full cost breakcompare_manufacturing_countries— Run the cost model across multiple manufacturing countries simultaneously to identify the optimal sourcing location. Returns P50/P80/P90 perreview_supplier_quote— Analyse a supplier quote against Costable's should-cost benchmarks. Returns a line-by-line delta (% over/under should-cost), verdict (LOW /
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:50:24 | ✓ | ✓ | 2101 ms | 85 | active |
| 2026-11-17 21:19:46 | ✓ | ✓ | 2779 ms | 85 | active |
| 2026-11-17 20:41:38 | ✓ | ✓ | 2140 ms | 85 | active |
| 2026-11-17 19:56:47 | ✓ | ✓ | 1183 ms | 85 | active |
| 2026-11-17 19:26:56 | ✓ | ✓ | 973 ms | 89 | active |
| 2026-11-17 18:47:37 | ✓ | ✓ | 2301 ms | 85 | active |
| 2026-11-17 18:26:10 | ✓ | ✓ | 2602 ms | 85 | active |
| 2026-11-17 17:41:49 | ✓ | ✓ | 2347 ms | 85 | active |
| 2026-11-17 16:56:39 | ✓ | ✓ | 1066 ms | 85 | active |
| 2026-11-17 16:26:24 | ✓ | ✓ | 1045 ms | 85 | active |
| 2026-11-17 15:40:05 | ✓ | ✓ | 2440 ms | 85 | active |
| 2026-11-17 14:42:10 | ✓ | ✓ | 2046 ms | 85 | active |
| 2026-11-17 13:57:53 | ✓ | ✓ | 917 ms | 89 | active |
| 2026-11-17 13:26:31 | ✓ | ✓ | 1134 ms | 85 | active |
| 2026-11-17 12:55:16 | ✓ | ✓ | 2151 ms | 85 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://costable.ai/api/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/costable-ai-api-mcp # JSON