# Costable — Parametric Should-Cost Analysis (remote · costable.ai)

Parametric should-cost: P50/P80/P90 estimates, 801 materials, 25 countries, quote review.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `costable.ai`: 77/100 (this document), [markdown](https://verifymcp.io/servers/1337mofo-costable/api-mcp.md), [page](https://verifymcp.io/servers/1337mofo-costable/api-mcp)

## Channel facts

- Endpoint: `https://costable.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 75/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1461 tokens (~146/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 97/100
  - Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the Costable — Parametric Should-Cost Analysis MCP server?

Costable — Parametric Should-Cost Analysis is a hosted endpoint at https://costable.ai/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http 1337mofo-costable 'https://costable.ai/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "1337mofo-costable": {
      "url": "https://costable.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "1337mofo-costable": {
      "type": "http",
      "url": "https://costable.ai/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.1337mofo-costable]
url = "https://costable.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "1337mofo-costable": {
      "type": "remote",
      "url": "https://costable.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add 1337mofo-costable --url 'https://costable.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  1337mofo-costable:
    url: "https://costable.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "1337mofo-costable": {
      "Transport": "http",
      "Url": "https://costable.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add 1337mofo-costable -t streamable-http -u 'https://costable.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "1337mofo-costable": {
      "type": "http",
      "url": "https://costable.ai/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-04 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (10)

### `estimate_part` (~217 tokens)

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.

Input parameters:

- `batchQty` (number): Batch / order quantity. Affects Wright's Law learning curve factor. Defaults to 100.
- `countryCode` (string): ISO 3166-1 alpha-2 manufacturing country code. Defaults to 'US'. Supported: US, CN, DE, JP, UK, MX, IN, VN, TH, PL, BR, FR, IT, KR, TW, CA, SE, SG, MY, ID, CZ, TR, ZA, ES, AU.
- `description` (string, required): Natural language description, e.g. '500 ABS injection moulded phone cases 0.08 kg' or 'CNC milled aluminium bracket 0.45 kg, 100 units'.

### `search_materials` (~139 tokens)

Search the Costable materials database (37 materials with LME-sourced pricing). Returns material name, category, price per kg, density, and strength properties.

Input parameters:

- `category` (string): Filter by category: Metals - Aluminium, Metals - Steel, Metals - Titanium, Metals - Copper Alloys, Polymers - Thermoplastic, Polymers - Thermoset, Composites, Timber, Rubber & Elastomers.
- `limit` (number): Maximum results to return. Defaults to 20.
- `query` (string): Search query, e.g. 'aluminium', 'stainless', 'ABS', 'titanium'.

### `search_processes` (~124 tokens)

Search the Costable manufacturing process database (41 processes). Returns process name, category, machine rate ($/hr), and cycle time model.

Input parameters:

- `category` (string): Filter by category: CNC Machining, Sheet Metal, Casting, Polymer Processing, Additive Manufacturing, Composites, Welding & Joining, Surface Finishing, Assembly.
- `limit` (number): Maximum results to return. Defaults to 20.
- `query` (string): Search query, e.g. 'CNC', 'injection moulding', 'laser cutting', 'anodising'.

### `get_labour_rates` (~79 tokens)

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).

Input parameters:

- `countryCode` (string, required): ISO 3166-1 alpha-2 country code, e.g. 'US', 'CN', 'DE', 'VN'.

### `create_cost_model` (~181 tokens)

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.

Input parameters:

- `batchQty` (number, required): Batch / order quantity. Affects Wright's Law learning curve.
- `countryCode` (string, required): Primary manufacturing country code (ISO 3166-1 alpha-2).
- `marginRate` (number): Profit margin as a decimal fraction (e.g. 0.15 = 15%). Defaults to 0.15.
- `name` (string, required): Descriptive name for the cost model, e.g. 'Aluminium Enclosure Rev2'.
- `overheadRate` (number): Factory overhead as a decimal fraction (e.g. 0.25 = 25%). Defaults to 0.25.

### `add_material_to_model` (~153 tokens)

Add a material (BOM line) to an existing cost model. Searches the materials database by name query — no need for exact IDs.

Input parameters:

- `massKg` (number, required): Mass of material per unit in kilograms.
- `materialQuery` (string, required): Material name to search for, e.g. 'ABS', 'Aluminium 6061', 'Stainless 304'.
- `modelId` (number, required): Cost model ID returned by create_cost_model.
- `qty` (number): Number of this material per unit assembly. Defaults to 1.
- `scrapFactor` (number): Scrap/yield factor (e.g. 1.05 = 5% material waste). Defaults to 1.05.

### `add_process_to_model` (~220 tokens)

Add a manufacturing process step to an existing cost model. Searches the process database by name query — no need for exact IDs.

Input parameters:

- `countryCode` (string, required): Country where this process step is performed (ISO 3166-1 alpha-2).
- `cycleTimeHrs` (number, required): Cycle time per unit in decimal hours (e.g. 0.5 = 30 minutes).
- `modelId` (number, required): Cost model ID returned by create_cost_model.
- `processQuery` (string, required): Process name to search for, e.g. 'CNC 3-Axis', 'Injection Moulding', 'TIG Welding'.
- `skillLevel` (string, required): Worker skill level. Options: cnc_machinist, machine_operator, welder, composite_tech, assembly_tech, quality_inspector, toolmaker, engineer, general_labour, painter, electrician, plumber, driver, war…
- `stepOrder` (number): Step sequence number (1 = first). Defaults to 1.

### `calculate_cost_model` (~70 tokens)

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).

Input parameters:

- `modelId` (number, required): Cost model ID returned by create_cost_model.

### `compare_manufacturing_countries` (~99 tokens)

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.

Input parameters:

- `countries` (array, required): Array of ISO 3166-1 alpha-2 country codes to compare, e.g. ['US','CN','VN','MX','DE']. Maximum 6.
- `modelId` (number, required): Cost model ID returned by create_cost_model.

### `review_supplier_quote` (~109 tokens)

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.

Input parameters:

- `countryCode` (string, required): Supplier's manufacturing country (ISO 3166-1 alpha-2).
- `items` (array, required): Quote line items.
- `supplierName` (string, required): Name of the supplier (for labelling the report).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/1337mofo-costable/api-mcp#diagnostics

## Score history

- 2026-09-20: 77
- 2026-09-19: 77
- 2026-09-18: 76
- 2026-09-17: 76
- 2026-09-16: 75
- 2026-09-15: 75
- 2026-09-14: 74
- 2026-09-13: 74
- 2026-09-12: 73
- 2026-09-11: 73
- 2026-09-10: 72
- 2026-09-09: 72
- 2026-09-08: 71
- 2026-09-07: 71
- 2026-09-06: 71
- 2026-09-05: 70
- 2026-09-04: 70
- 2026-09-03: 69
- 2026-09-02: 69
- 2026-09-01: 68
- 2026-08-31: 68
- 2026-08-30: 67
- 2026-08-29: 67
- 2026-08-28: 66
- 2026-08-27: 66
- 2026-08-26: 65
- 2026-08-25: 63
- 2026-08-24: 62
- 2026-08-23: 62
- 2026-08-22: 61

## Common questions

### What is the Costable — Parametric Should-Cost Analysis MCP server?

Costable — Parametric Should-Cost Analysis is an MCP server listed in the public MCP registry as io.github.1337mofo/costable. Parametric should-cost: P50/P80/P90 estimates, 801 materials, 25 countries, quote review. This page covers its hosted endpoint (https://costable.ai/api/mcp).

### Is the Costable — Parametric Should-Cost Analysis MCP server safe to use?

Costable — Parametric Should-Cost Analysis scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Costable — Parametric Should-Cost Analysis MCP server expose?

Costable — Parametric Should-Cost Analysis exposes 10 tools: estimate_part, search_materials, search_processes, get_labour_rates, create_cost_model, and 5 more. Their descriptions and schemas cost roughly 1,391 tokens of context every time the server is loaded.

### Does the Costable — Parametric Should-Cost Analysis MCP server require authentication?

No. We connected to Costable — Parametric Should-Cost Analysis without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Costable — Parametric Should-Cost Analysis MCP server still maintained?

Costable — Parametric Should-Cost Analysis is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://costable.ai/api/mcp
- Changelog RSS feed: https://verifymcp.io/servers/1337mofo-costable/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/1337mofo-costable/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/1337mofo-costable/api-mcp