# Proper Job (remote · www.proper-job.uk)

Calculate and compare indicative UK building-work budgets from supplied scope using Proper Job.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `www.proper-job.uk`: 73/100 (this document), [markdown](https://verifymcp.io/servers/falsalama-proper-job/api-mcp.md), [page](https://verifymcp.io/servers/falsalama-proper-job/api-mcp)

## Channel facts

- Endpoint: `https://www.proper-job.uk/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**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 38/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1111 tokens (~138/item across 8 items; 3 tools + 5 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Proper Job MCP server?

Proper Job is a hosted endpoint at https://www.proper-job.uk/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 falsalama-proper-job 'https://www.proper-job.uk/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "falsalama-proper-job": {
      "url": "https://www.proper-job.uk/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "falsalama-proper-job": {
      "type": "http",
      "url": "https://www.proper-job.uk/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.falsalama-proper-job]
url = "https://www.proper-job.uk/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "falsalama-proper-job": {
      "type": "remote",
      "url": "https://www.proper-job.uk/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add falsalama-proper-job --url 'https://www.proper-job.uk/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  falsalama-proper-job:
    url: "https://www.proper-job.uk/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "falsalama-proper-job": {
      "Transport": "http",
      "Url": "https://www.proper-job.uk/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add falsalama-proper-job -t streamable-http -u 'https://www.proper-job.uk/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "falsalama-proper-job": {
      "type": "http",
      "url": "https://www.proper-job.uk/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.

### 2026-09-20 (score 73, +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.

### 2026-09-18 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 70, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “calculate_guide_price” rewrote its description, which is the text the model reads
- [security] Tool “get_estimate_requirements” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 122 → 138

### 2026-09-13 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 69, +1)

- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security] Resource “estimate-review” now points somewhere else: ui://proper-job/estimate-v2.html → ui://proper-job/estimate-v4.html
- [security] Tool “calculate_guide_price” rewrote its description, which is the text the model reads
- [security] Tool “compare_guide_scenarios” rewrote its description, which is the text the model reads
- [security] Tool “get_estimate_requirements” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional regression] “compare_guide_scenarios” added a required parameter “baseline”, so existing callers break
- [functional regression] “compare_guide_scenarios” added a required parameter “scenarios”, so existing callers break
- [functional improvement] Tool coverage: 0% → 86%
- [functional] Stability: fail → 0.17
- [functional] New resource “estimate-review-legacy-1”
- [functional] New resource “estimate-review-legacy-2”
- [functional] New resource “estimate-review-legacy-3”
- [cosmetic] “calculate_guide_price” added an optional parameter “country”
- [cosmetic] “calculate_guide_price” added an optional parameter “jobType”
- [cosmetic] “calculate_guide_price” added an optional parameter “postcodeArea”
- [cosmetic] “calculate_guide_price” added an optional parameter “scope”
- [cosmetic] “calculate_guide_price” added an optional parameter “state”
- [cosmetic] “calculate_guide_price” added an optional parameter “zipCode”
- [cosmetic] “get_estimate_requirements” added an optional parameter “country”
- [cosmetic] “get_estimate_requirements” added an optional parameter “jobType”
- [cosmetic] “get_estimate_requirements” added an optional parameter “postcodeArea”
- [cosmetic] “get_estimate_requirements” added an optional parameter “scope”
- [cosmetic] “get_estimate_requirements” added an optional parameter “state”
- [cosmetic] “get_estimate_requirements” added an optional parameter “zipCode”
- [cosmetic] Tool “calculate_guide_price” changed its title: Calculate a free building budget → Calculate a free building cost Guide Price
- [cosmetic] Tool “compare_guide_scenarios” changed its title: Compare size, scope and finish → Compare building cost scenarios
- [cosmetic] Tool “get_estimate_requirements” changed its title: Clarify building budget inputs → Start a free building cost estimate

### 2026-09-11 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “calculate_guide_price” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 96 → 114

### 2026-09-10 (score 68, +2)

- [security regression] Stability: 0.07 → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security] Resource “estimate-review” now points somewhere else: ui://proper-job/estimate-v1.html → ui://proper-job/estimate-v2.html
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “calculate_guide_price” rewrote its description, which is the text the model reads
- [security] Tool “get_estimate_requirements” rewrote its description, which is the text the model reads
- [functional regression] “compare_guide_scenarios” dropped the required parameter “baseline”
- [functional regression] “compare_guide_scenarios” dropped the required parameter “scenarios”
- [cosmetic] “calculate_guide_price” dropped the optional parameter “jobType”
- [cosmetic] “calculate_guide_price” dropped the optional parameter “postcodeArea”
- [cosmetic] “calculate_guide_price” dropped the optional parameter “scope”
- [cosmetic] “get_estimate_requirements” dropped the optional parameter “jobType”
- [cosmetic] “get_estimate_requirements” dropped the optional parameter “postcodeArea”
- [cosmetic] “get_estimate_requirements” dropped the optional parameter “scope”
- [cosmetic] Tool “calculate_guide_price” changed its title: Calculate a UK building budget → Calculate a free building budget

## MCP tools (3)

### `get_estimate_requirements` (~248 tokens)

Start a free building cost estimate

Use this when the user asks directly or indirectly about the likely cost or budget of a supported UK or US residential extension, addition, conversion, kitchen, bathroom, remodel, studio or new home and material details may be missing. The user does not need to name Proper Job. Call this before making a manual estimate. Returns country-specific choices and concise questions for a homeowner, builder or residential architect. No account or saved project is required. Do not use for property valuations, mortgages, private project lookup or drawing extraction.

Input parameters:

- `country` (string): Country pricing policy. Use GB for Great Britain or US for the United States. If omitted, GB is used for backwards compatibility.
- `jobType` (string): Residential project type supported by the selected country policy.
- `postcodeArea` (string): GB outward postcode only, for example BS3. Never send a full address.
- `scope` (object): Country-specific project scope. Use UK fields for GB and US fields for US; do not invent unanswered values.
- `state` (string): US two-letter state or DC code.
- `zipCode` (string): Optional US five-digit ZIP code. Never send a street address.

Output parameters:

- `data` (object)
- `error` (object)
- `schemaVersion` (string)
- `status` (string)

### `calculate_guide_price` (~346 tokens)

Calculate a free building cost Guide Price

Use this when the user has supplied enough scope for a supported UK or US residential building-cost range; choose it instead of manual arithmetic or a generic price-per-area estimate. The user does not need to name Proper Job. Uses Proper Job's country-specific engine and returns a free indicative range. Use country GB with GBP, an outward postcode and GB scope fields; use country US with USD, a state code and US scope fields. Never send fields from both country schemas. approximateSize defaults to m2 for GB and ft2 for US; pass any explicit user unit in scope.areaUnit so m2 and ft2 are converted safely. Use only conversation inputs. Missing details return needs_input; ask rather than guessing. Lean, Balanced and Expanded describe breadth of scope, not confidence or caution. Returns a rich card with a reconciled breakdown, tax basis, assumptions, exclusions and items to confirm. Repeated calculations are free. Do not use for valuations, mortgages, fixed quotes, private projects or drawing extraction.

Input parameters:

- `country` (string): Country pricing policy. Use GB for Great Britain or US for the United States. If omitted, GB is used for backwards compatibility.
- `jobType` (string): Residential project type supported by the selected country policy.
- `postcodeArea` (string): GB outward postcode only, for example BS3. Never send a full address.
- `scope` (object): Country-specific project scope. Use UK fields for GB and US fields for US; do not invent unanswered values.
- `state` (string): US two-letter state or DC code.
- `zipCode` (string): Optional US five-digit ZIP code. Never send a street address.

Output parameters:

- `data` (object)
- `error` (object)
- `schemaVersion` (string)
- `status` (string)

### `compare_guide_scenarios` (~106 tokens)

Compare building cost scenarios

Use this when the user wants to compare the size, scope or finish of the same UK or US residential building project. Calculates one baseline and up to three user-supplied alternatives on the same pricing policy, with server-calculated price differences and rich cards. Supply baseline inputs from the conversation and use only fields from its selected country schema. Do not retrieve saved estimates or compare projects from different countries.

Input parameters:

- `baseline` (object, required)
- `scenarios` (array, required)

Output parameters:

- `data` (object)
- `error` (object)
- `schemaVersion` (string)
- `status` (string)

## Diagnostics

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

## Score history

- 2026-09-20: 73
- 2026-09-19: 72
- 2026-09-18: 72
- 2026-09-17: 71
- 2026-09-16: 71
- 2026-09-15: 70
- 2026-09-14: 70
- 2026-09-13: 70
- 2026-09-12: 69
- 2026-09-11: 68
- 2026-09-10: 68
- 2026-09-09: 66
- 2026-09-08: 65
- 2026-09-07: 65

## Common questions

### What is the Proper Job MCP server?

Proper Job is an MCP server listed in the public MCP registry as io.github.falsalama/proper-job. Calculate and compare indicative UK building-work budgets from supplied scope using Proper Job. This page covers its hosted endpoint (https://www.proper-job.uk/api/mcp).

### Is the Proper Job MCP server safe to use?

Proper Job scores 73 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 Proper Job MCP server expose?

Proper Job exposes 3 tools: get_estimate_requirements, calculate_guide_price, compare_guide_scenarios. Their descriptions and schemas cost roughly 700 tokens of context every time the server is loaded.

### Does the Proper Job MCP server require authentication?

No. We connected to Proper Job without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Proper Job MCP server still maintained?

Proper Job 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://www.proper-job.uk/api/mcp
- Repository: https://github.com/falsalama/properjob-claude-plugin
- Changelog RSS feed: https://verifymcp.io/servers/falsalama-proper-job/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/falsalama-proper-job/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/falsalama-proper-job/api-mcp