# Costable — Parametric Should-Cost Analysis

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

- name: io.github.1337mofo/costable
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 73/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.1337mofo%2Fcostable
- tools: https://api.protogrid.dev/v1/servers/io.github.1337mofo%2Fcostable/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 99
- freshness: 85
- provenance: 35
- drivers: +reachable +uptime-98% ~updated-59d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: estimate_part (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_cost_model (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); calculate_cost_model (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,819 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 10, about 1,819 tokens to load them all
- tool set hash: 4cb14b58025e7bcf470f74e11e632658
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.1337mofo/costable.svg)](https://protogrid.dev/servers/io.github.1337mofo/costable)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://costable.ai/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.9831933)

## Packages

_none_

## Tools (10)

- `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.
- `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 breakdown (material, labour, machine, overhead, margin).
- `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.
- `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.
- `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 uncertainty. Use this for quick feasibility checks before building a full cost model.
- `get_labour_rates`: Get manufacturing labour rates ($/hr) for all skill levels in a given country. Data covers 16 skill levels across 25 countries (ILO/BLS/ABS sourced).
- `review_supplier_quote`: Analyse a supplier quote against Costable's should-cost benchmarks. Returns a line-by-line delta (% over/under should-cost), verdict (LOW / COMPETITIVE / HIGH / VERY HIGH), and a list of the top items to challenge in negotiation.
- `search_materials`: Search the Costable materials database (37 materials with LME-sourced pricing). Returns material name, category, price per kg, density, and strength properties.
- `search_processes`: Search the Costable manufacturing process database (41 processes). Returns process name, category, machine rate ($/hr), and cycle time model.