# ai.clarx/mcp (npm · @clarxai/mcp)

Score agent manifests, generate CI workflows, and pull Clarx scan findings into your IDE.

- Trust score: 63/100 (medium)
- Change this week: +45
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@clarxai/mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/ai-clarx-mcp/clarxai-mcp.md), [page](https://verifymcp.io/servers/ai-clarx-mcp/clarxai-mcp)

## Channel facts

- Registry: `npm`
- Package: `@clarxai/mcp`
- Version: `0.2.1`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 26 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 413 tokens (~137/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add ai-clarx-mcp -- npx -y @clarxai/mcp
```

### Codex

```bash
codex mcp add ai-clarx-mcp -- npx -y @clarxai/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-clarx-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@clarxai/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-clarx-mcp --command npx --arg -y --arg @clarxai/mcp
```

### Hermes

```yaml
mcp_servers:
  ai-clarx-mcp:
    command: "npx"
    args: ["-y", "@clarxai/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "ai-clarx-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clarxai/mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 63, +48)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 15, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 0, −40)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 40, +22)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: unverified
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail

### 2026-07-27 (score 18)

First indexed and scored.

## MCP tools (3)

### `analyze_manifest` (~158 tokens)

Score an agent manifest

Score CLAUDE.md / AGENTS.md manifest content with the same rules as the Clarx manifest studio. Returns an overall quality estimate (0-100), per-pillar scores, findings with line numbers, and a section checklist. This is a manifest quality estimate — do not compare it to Clarx repo AI-readiness scores, which use a different rule system.

Input parameters:

- `content` (string): Full markdown body of the manifest. Pass this or file_path, not both.
- `file_path` (string): Path to the manifest file (resolved against the server working directory, typically the workspace root). Preferred — avoids inlining the file into the conversation.
- `include_outline` (boolean): Include the heading outline (section tree with line numbers).

### `analyze_clarx_manifest` (~89 tokens)

Validate clarx-manifest.json

Validate a clarx-manifest.json machine manifest against the Clarx engine schema. Returns recognized keys, errors, and suggestions for keys worth declaring (generated dirs, hubs, verification commands).

Input parameters:

- `content` (string): Raw JSON content. Pass this or file_path, not both.
- `file_path` (string): Path to clarx-manifest.json (resolved against the server working directory).

### `get_ci_workflow` (~166 tokens)

Generate Clarx CI workflow

Generate a GitHub Actions workflow YAML that gates pull requests on the Clarx AI-readiness score (npx @clarxai/cli). Write the result to .github/workflows/clarx.yml.

Input parameters:

- `cli_version` (string): @clarxai/cli version to pin.
- `ignore_patterns` (array): Glob patterns to exclude from scoring, e.g. ['vendor/**'].
- `min_pillar_score` (number|null): Optional per-pillar floor.
- `min_score` (number): Fail the check when the overall score is below this (0-100).
- `upload_artifact` (boolean): Attach a markdown report artifact to the run.
- `upload_sarif` (boolean): Upload findings as SARIF to GitHub code scanning.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-clarx-mcp/clarxai-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 15
- 2026-07-31: 0
- 2026-07-30: 40
- 2026-07-28: 40
- 2026-07-27: 18

## Links

- npm package: https://www.npmjs.com/package/@clarxai/mcp
- Socket report: https://socket.dev/npm/package/@clarxai/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-clarx-mcp/clarxai-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-clarx-mcp/clarxai-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-clarx-mcp/clarxai-mcp