Costable — Parametric Should-Cost Analysis
Server Details
Parametric should-cost: P50/P80/P90 estimates, 801 materials, 25 countries, quote review.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 10 tools
Most tools map cleanly to distinct actions, but estimate_part, calculate_cost_model, and compare_manufacturing_countries all produce cost estimates and could be confused. The descriptions clarify their different scopes enough for a capable agent, but the boundary is not as crisp as it could be.
All tool names follow a consistent snake_case verb_noun pattern with clear verbs: add_, calculate_, compare_, create_, estimate_, get_, review_, search_. There are no mixed conventions or vague action names.
Ten tools is well-scoped for a should-cost analysis domain. Each tool supports a distinct step in the workflow—data lookup, model creation, population, calculation, comparison, quick estimation, and quote review—without unnecessary bloat.
The server covers creation, population, calculation, country comparison, quick estimation, and supplier quote review well. However, there are no update, delete, list, or get operations for cost models, and no way to remove or edit materials/processes once added, which creates dead ends when iterating on a model.
Available Tools
10 toolsadd_material_to_modelAInspect
Add a material (BOM line) to an existing cost model. Searches the materials database by name query — no need for exact IDs.
Inputs: massKg (required), modelId (required), materialQuery (required), qty, +1 more.
add_process_to_modelAInspect
Add a manufacturing process step to an existing cost model. Searches the process database by name query — no need for exact IDs.
Inputs: modelId (required), skillLevel (required), countryCode (required), cycleTimeHrs (required), +2 more.
calculate_cost_modelAInspect
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 breakdown (material, labour, machine, overhead, margin).
Inputs: modelId (required).
compare_manufacturing_countriesAInspect
Run the cost model across multiple manufacturing countries simultaneously to identify the optimal sourcing location. Returns P50/P80/P90 per country and % delta vs baseline.
Inputs: modelId (required), countries (required).
create_cost_modelBInspect
Create a new parametric cost model in Costable. Returns the model ID which is used by add_material_to_model, add_process_to_model, calculate_cost_model, and compare_manufacturing_countries.
Inputs: name (required), batchQty (required), countryCode (required), marginRate, +1 more.
estimate_partAInspect
Instantly estimate the should-cost of a manufactured part using natural language. Returns P50 (median), P80 and P90 cost-at-risk per unit based on Monte Carlo simulation of material price variance, labour rate variance and cycle time uncertainty. Use this for quick feasibility checks before building a full cost model.
Inputs: description (required), batchQty, countryCode.
get_labour_ratesAInspect
Get manufacturing labour rates ($/hr) for all skill levels in a given country. Data covers 16 skill levels across 25 countries (ILO/BLS/ABS sourced).
Inputs: countryCode (required).
review_supplier_quoteAInspect
Analyse a supplier quote against Costable's should-cost benchmarks. Returns a line-by-line delta (% over/under should-cost), verdict (LOW / COMPETITIVE / HIGH / VERY HIGH), and a list of the top items to challenge in negotiation.
Inputs: items (required), countryCode (required), supplierName (required).
search_materialsAInspect
Search the Costable materials database (37 materials with LME-sourced pricing). Returns material name, category, price per kg, density, and strength properties.
Inputs: limit, query, category.
search_processesAInspect
Search the Costable manufacturing process database (41 processes). Returns process name, category, machine rate ($/hr), and cycle time model.
Inputs: limit, query, category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Instant parametric cost estimates for custom manufacturing: CNC, molding, sheet metal, 3DP, PCB.
Should-cost of a machined, sheet metal or cast part from its PDF, DXF or STEP drawing, line by line.
Quoting, pricing, production and part data for contract manufacturers (3D printing, CNC).
Packaging material prices, quote checks, contract price adjustments, pack costing and supplier RFQs.
Related MCP Servers
- FlicenseAqualityBmaintenanceParametric price benchmarking for engineering and procurement trade-offs. Agentic first, runs on your data, stays on your machine.122-
- AlicenseNot gradedqualityDmaintenanceIntelligently generates cost estimates and lead times for manufacturing RFPs by parsing requests, matching against historical quotes, and calculating activity-based costs with confidence scoring and human approval workflows.MIT
- FlicenseNot gradedqualityDmaintenanceConnects Hermes to procurement pricing tools for BOM review, mock market data, cost calculations, and Excel report generation.-
- AlicenseNot gradedqualityBmaintenanceExposes 19 tools over HTTP (search_items, compare_bom, etc.) that let an agent read and write the same local SQLite procurement library a human edits in the desktop UI, ingesting materials and prices from Excel, CSV, Word, text-layer PDFs and OCR'd scans after human preview, and comparing BOMs against historical purchase records with full source/date traceability. Prices are only ever drawn from stored records — unmatched items go to an unmatched list instead of being estimated.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.