# io.github.andypgray/loadbearing (nuget · Zphil.LoadBearing.Cli)

Checks .NET solutions against a fluent C# architecture spec and explains the rules to agents.

- Trust score: 85/100 (high trust)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- nuget · `Zphil.LoadBearing.Cli`: 85/100 (this document), [markdown](https://verifymcp.io/servers/andypgray-loadbearing/zphil-loadbearing-cli.md), [page](https://verifymcp.io/servers/andypgray-loadbearing/zphil-loadbearing-cli)

## Channel facts

- Registry: `nuget`
- Package: `Zphil.LoadBearing.Cli`
- Version: `0.8.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 74/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2616 tokens (~523/item across 5 items; 5 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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the io.github.andypgray/loadbearing MCP server?

io.github.andypgray/loadbearing runs locally as a NuGet package, launched with dnx Zphil.LoadBearing.Cli@0.8.0 --yes. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add andypgray-loadbearing -- dnx Zphil.LoadBearing.Cli@0.8.0 --yes
```

### Cursor

```json
{
  "mcpServers": {
    "andypgray-loadbearing": {
      "command": "dnx",
      "args": [
        "Zphil.LoadBearing.Cli@0.8.0",
        "--yes"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "andypgray-loadbearing": {
      "command": "dnx",
      "args": [
        "Zphil.LoadBearing.Cli@0.8.0",
        "--yes"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add andypgray-loadbearing -- dnx Zphil.LoadBearing.Cli@0.8.0 --yes
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "andypgray-loadbearing": {
      "type": "local",
      "command": [
        "dnx",
        "Zphil.LoadBearing.Cli@0.8.0",
        "--yes"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  andypgray-loadbearing:
    command: "dnx"
    args: ["Zphil.LoadBearing.Cli@0.8.0", "--yes"]
```

### Netclaw

```json
{
  "McpServers": {
    "andypgray-loadbearing": {
      "Transport": "stdio",
      "Command": "dnx",
      "Arguments": [
        "Zphil.LoadBearing.Cli@0.8.0",
        "--yes"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "andypgray-loadbearing": {
      "command": "dnx",
      "args": [
        "Zphil.LoadBearing.Cli@0.8.0",
        "--yes"
      ]
    }
  }
}
```

## 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 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 83, −2)

- [functional] Stability: pass → 0.87

### 2026-09-16 (score 85, 0)

- [security] Stability: 0.97 → pass

### 2026-09-15 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 84, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-12 (score 68, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.7.0 → 0.8.0

### 2026-09-09 (score 82, −3)

- [functional] Stability: pass → 0.77

## MCP tools (5)

### `arch_explain` (~61 tokens)

Architecture Explain

Return one rule's because, fix, posture payload, and linked prose as text.

Input parameters:

- `ruleId` (string, required): A post-desugar rule ID as one string, not an array — e.g. layering/domain-independent or legacy/billing/containment.

### `arch_check` (~620 tokens)

Architecture Check

Run the architecture spec against the bound solution and return the JSON check report (schemaVersion 3): rules[] keyed by id, plus summary counts. Violations are data — a red rule is a finding, not an error. The rules parameter narrows what is evaluated, and the report then covers only those. Narrow with overview, skeleton or index (coarser grain) or rules (fewer rules); an over-budget report coarsens its own grain, as far as index, rather than being cut — and index lists every rule ID, which is what rules globs match. subjectTypes/subjectGeneratedTypes appear together on a rule whose subject contained generator output, pass or fail: how many types it swept and how many nobody wrote. Both absent means none were. Narrowing the rule with .Authored() removes them. If projects fail to load, or their NuGet packages did not resolve, the report still returns, stamped modelIncomplete: true and failedProjects/restoreFailedProjects — a verdict reached against a partial model; report that, never plain green. Under a .slnf solution filter, uncheckedProjects names the declared projects the run never checked — a clean report then covers a subset; say so. unsupportedProjects names the declared projects this product cannot read at all (C# only), each with its reason — no rule can be violated in one, so a clean report over a polyglot solution is not a clean solution either. multiTargetedProjects names the projects that compiled for several frameworks, each with the framework its shared types' facts follow — what another framework's #if guards was never in the model, so a clean report over such a project covers one framework's view of it.

Input parameters:

- `diffBase` (string): Git ref as one string, not an array; files changed since it that fall in a quarantined or cautioned scope raise a tripwire warning.
- `index` (boolean): Elide the rule prose too — sentence, because and fix — and the workspaceDiagnostics stream (workspaceDiagnosticCount says how many), keeping every rule's id, posture, status, baseline, warnings and v…
- `overview` (boolean): Elide each violation's sites, keeping every rule and every violation; siteCount (always present) still says how many. Coarser grain, never a narrower subject.
- `rules` (string): Rule-ID globs as one string, not an array, semicolon-separated ('*' spans '/'). Only matching rules run, so rules[] and summary cover that subset alone. Matching no rule is an error listing the avail…
- `skeleton` (boolean): Elide the violations too, keeping every rule with its verdict, prose, baseline and warnings; violationCount (always present) still says how many. Coarser than overview, still not a narrower subject.

### `arch_graph` (~880 tokens)

Architecture Graph

Return the JSON codebase survey (schemaVersion 1): projects[] with namespace inventories, projectEdges[] (source/target, declared vs observed dependencies), and externalEdges[] grouped by namespace root. Every project the workspace loaded is here, which is wider than the solution: solutionMember false marks a passenger a ProjectReference dragged in, and an absent key means membership was unreadable. projectEdges[] carry only references the code declares: where one source file is compiled into several projects, a project referencing its own compiled-in copy is not an edge to the declarer the type was attributed to, and multiplyDeclaredTypes[] names those types with every declaring project and the one whose facts won — arch.Project() on any declarer selects them, with rule verdicts answering from the winner's facts (the key is absent when the solution has none). shadowedTypes[] is the other coverage key: a full name a project declares that a referenced assembly also supplies means two types, so a rule naming it reaches both while arch.Project() over the declaring project reaches only the declaration. generated qualifies the types count on a project and on each namespace (absent when zero): how many of them a generator emitted, which is what arch.Project() would sweep and .Authored() would drop. A namespace whose two counts are equal is wholly generator output — never make it a layer glob. targetFrameworks rides every project's row and names what it declares, normalized (a project predating the SDK reads net48); factsFollow rides only a multi-targeted one and names the framework its shared types' facts came from — what another framework's #if guards is not in the model. isPackable, locksPackages and packageReferences are the artifact facts, evaluated rather than read off the project file, so a value an SDK defaults or a props file above the solution sets is the one reported; packageReferences is what the project declares, never the transitive closure. Needs no spec —…

Input parameters:

- `allowWorkspaceDiagnostics` (boolean): Survey the partial model even when some projects fail to load; otherwise the call returns an error naming what failed, because a survey missing whole projects is a wrong map, not a smaller one.
- `index` (boolean): Elide each project's declared references and target frameworks too, the observed project edges with them (projectEdgeCount says how many), and the workspaceDiagnostics stream (workspaceDiagnosticCoun…
- `overview` (boolean): Elide every project's namespace inventory, keeping every project, edge and external row. Coarser grain, never a narrower subject.
- `projects` (string): Project-name globs as one string, not an array, semicolon-separated ('*' allowed). References in both directions are kept, so an edge can name a project outside the scope. Matching no project is an e…
- `skeleton` (boolean): Elide the namespace inventories, the external-reference rows, the multiply-declared types and the shadowed names, keeping every project, its declared references and type count, and the observed proje…

### `arch_context` (~219 tokens)

Architecture Context

Return the architecture scope card(s) covering a path — a quarantined scope's dragons + sanctioned surface, a cautioned scope's dragons, or a layer's local rules — or a pointer line when none apply. If projects fail to load or to restore, the answer opens with a caveat naming them: cards from unloaded projects cannot be placed, and a rule about a package the restore never fetched was never measured, so treat a no-coverage answer as unproven there. A .slnf solution filter gets the same caveat for the declared projects it left unchecked: treat a no-coverage answer as unproven under them as well.

Input parameters:

- `path` (string, required): A file or directory path (absolute or solution-relative) as one string, not an array, to find architecture scope cards for. A path no card covers — including one the codebase does not contain yet — a…

### `arch_status` (~140 tokens)

Architecture Status

Return the JSON migration burndown (schemaVersion 2): per-rule grandfathered/stale counts and promotion suggestions. If projects fail to load, or their NuGet packages did not resolve, the burndown still returns, stamped modelIncomplete: true and failedProjects/restoreFailedProjects — counts from a partial model; report that rather than quoting them as whole. Under a .slnf solution filter, uncheckedProjects names the declared projects the run never checked; they contribute no violations, so every count reads low. unsupportedProjects names the declared projects this product cannot read at all (C# only): their zero is permanent, not burndown.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/andypgray-loadbearing/zphil-loadbearing-cli#diagnostics

## Score history

- 2026-09-20: 85
- 2026-09-19: 84
- 2026-09-18: 84
- 2026-09-17: 83
- 2026-09-16: 85
- 2026-09-15: 85
- 2026-09-14: 84
- 2026-09-13: 84
- 2026-09-12: 68
- 2026-09-11: 82
- 2026-09-10: 82
- 2026-09-09: 82
- 2026-09-08: 85
- 2026-09-07: 84
- 2026-09-06: 84
- 2026-09-05: 83
- 2026-09-04: 83
- 2026-09-03: 82
- 2026-09-02: 82
- 2026-09-01: 82
- 2026-08-31: 81
- 2026-08-30: 81
- 2026-08-29: 80
- 2026-08-28: 80
- 2026-08-27: 79
- 2026-08-26: 79
- 2026-08-25: 78
- 2026-08-24: 77
- 2026-08-23: 77
- 2026-08-22: 76

## Common questions

### What is the io.github.andypgray/loadbearing MCP server?

io.github.andypgray/loadbearing is an MCP server listed in the public MCP registry as io.github.andypgray/loadbearing. Checks .NET solutions against a fluent C# architecture spec and explains the rules to agents. This page covers its NuGet package (Zphil.LoadBearing.Cli).

### Is the io.github.andypgray/loadbearing MCP server safe to use?

io.github.andypgray/loadbearing scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 io.github.andypgray/loadbearing MCP server expose?

io.github.andypgray/loadbearing exposes 5 tools: arch_explain, arch_check, arch_graph, arch_context, arch_status. Their descriptions and schemas cost roughly 1,920 tokens of context every time the server is loaded.

### Is the io.github.andypgray/loadbearing MCP server still maintained?

io.github.andypgray/loadbearing 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.

### What licence is the io.github.andypgray/loadbearing MCP server under?

io.github.andypgray/loadbearing declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- NuGet package: https://www.nuget.org/packages/Zphil.LoadBearing.Cli
- Socket report: https://socket.dev/nuget/package/Zphil.LoadBearing.Cli
- Repository: https://github.com/andypgray/loadbearing
- Changelog RSS feed: https://verifymcp.io/servers/andypgray-loadbearing/zphil-loadbearing-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/andypgray-loadbearing/zphil-loadbearing-cli.json
- HTML version of this page: https://verifymcp.io/servers/andypgray-loadbearing/zphil-loadbearing-cli