Costable — Parametric Should-Cost Analysis is a remote MCP server that gives an AI agent 10 tools, among them add_material_to_model, add_process_to_model, calculate_cost_model. It answers at https://costable.ai/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Parametric should-cost: P50/P80/P90 estimates, 801 materials, 25 countries, quote review.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_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. Inputs: modelId, materialQuery, massKg, qty, scrapFactor |
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. Inputs: modelId, processQuery, countryCode, skillLevel, cycleTimeHrs, stepOrder |
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 breakdown (material, labour, machine, overhead, margin). Inputs: modelId |
compare_manufacturing_countries | 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, countries |
create_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, calculate_cost_model, and compare_manufacturing_countries. Inputs: name, countryCode, batchQty, overheadRate, marginRate |
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 based on Monte Carlo simulation of material price variance, labour rate variance and cycle time uncert Inputs: description, countryCode, batchQty |
get_labour_rates | Get manufacturing labour rates ($/hr) for all skill levels in a given country. Data covers 16 skill levels across 25 countries (ILO/BLS/ABS sourced). Inputs: countryCode |
review_supplier_quote | Analyse a supplier quote against Costable's should-cost benchmarks. Returns a line-by-line delta (% over/under should-cost), verdict (LOW / COMPETITIVE / HIGH / VERY HIGH), and a list of the top items to challenge in negotiation. Inputs: supplierName, countryCode, items |
search_materials | Search the Costable materials database (37 materials with LME-sourced pricing). Returns material name, category, price per kg, density, and strength properties. Inputs: query, category, limit |
search_processes | Search the Costable manufacturing process database (41 processes). Returns process name, category, machine rate ($/hr), and cycle time model. Inputs: query, category, limit |
Every block below points at https://costable.ai/api/mcp. Pick your client and copy.
claude mcp add --transport http costable-parametric-should-cost https://costable.ai/api/mcp
{
"mcpServers": {
"costable-parametric-should-cost": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://costable.ai/api/mcp"]
}
}
}{
"mcpServers": {
"costable-parametric-should-cost": {
"url": "https://costable.ai/api/mcp"
}
}
}{
"servers": {
"costable-parametric-should-cost": {
"type": "http",
"url": "https://costable.ai/api/mcp"
}
}
}{
"context_servers": {
"costable-parametric-should-cost": {
"url": "https://costable.ai/api/mcp"
}
}
}{
"mcpServers": {
"costable-parametric-should-cost": {
"serverUrl": "https://costable.ai/api/mcp"
}
}
}{
"mcpServers": {
"costable-parametric-should-cost": {
"url": "https://costable.ai/api/mcp"
}
}
}name: Costable — Parametric Should-Cost Analysis
version: 0.0.1
schema: v1
mcpServers:
- name: Costable — Parametric Should-Cost Analysis
type: streamable-http
url: https://costable.ai/api/mcp{
"mcpServers": {
"costable-parametric-should-cost": {
"httpUrl": "https://costable.ai/api/mcp"
}
}
}{
"mcpServers": {
"costable-parametric-should-cost": {
"type": "http",
"url": "https://costable.ai/api/mcp"
}
}
}{
"mcpServers": {
"costable-parametric-should-cost": {
"url": "https://costable.ai/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fcostable.ai%2Fapi%2Fmcp&type=streamable_http&id=costable-parametric-should-cost&name=Costable%20%E2%80%94%20Parametric%20Should-Cost%20Analysis
It answered our last check on 19 October 2026 in 523 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
10, as returned by the server's own tools/list on 12 September 2026: add_material_to_model, add_process_to_model, calculate_cost_model, compare_manufacturing_countries, create_cost_model, estimate_part, get_labour_rates, review_supplier_quote, and 2 more.
It answered our last check on 19 October 2026 in 523 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://costable.ai/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.1337mofo. Endpoint host: costable.ai. ARD identifier: urn:air:io.github.1337mofo:mcp:costable.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.