# io.github.archonics/mcp-audit (npm · @archonics/mcp-audit)

Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan.

- Trust score: 67/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-06

## Components

- npm · `@archonics/mcp-audit`: 67/100 (this document), [markdown](https://verifymcp.io/servers/archonics-mcp-audit/archonics-mcp-audit.md), [page](https://verifymcp.io/servers/archonics-mcp-audit/archonics-mcp-audit)

## Channel facts

- Registry: `npm`
- Package: `@archonics/mcp-audit`
- Version: `0.1.4`
- 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 2026-08-06.

- **Supply Chain Security**: 78/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects @anthropic-ai/sdk 0.90.0, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 98 of 102 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - 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 84 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 652 tokens (~217/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**: 37/100
  - Stability observed for 11 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 archonics-mcp-audit -- npx -y @archonics/mcp-audit
```

### Codex

```bash
codex mcp add archonics-mcp-audit -- npx -y @archonics/mcp-audit
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add archonics-mcp-audit --command npx --arg -y --arg @archonics/mcp-audit
```

### Hermes

```yaml
mcp_servers:
  archonics-mcp-audit:
    command: "npx"
    args: ["-y", "@archonics/mcp-audit"]
```

### Other

```json
{
  "mcpServers": {
    "archonics-mcp-audit": {
      "command": "npx",
      "args": [
        "-y",
        "@archonics/mcp-audit"
      ]
    }
  }
}
```

## 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.

### 2026-08-06 (score 67, +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.

### 2026-08-05 (score 66, 0)

- [security improvement] CVE-2026-69207 no longer affects this package

### 2026-08-04 (score 66, +1)

- [security regression] CVE-2026-69207 affects this package: medium

### 2026-08-03 (score 65, +45)

- [security regression] CVE-2026-41686 affects this package: medium
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Stability: unverified → 0.27
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-02 (score 20, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-08-01 (score 20, +1)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-31 (score 19, −25)

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

### 2026-07-27 (score 44)

First indexed and scored.

## MCP tools (3)

### `audit_system_prompt` (~225 tokens)

Analyzes a system prompt for context engineering issues and returns the top 3 findings from the Archonics free-tier scan. Use this when a user shares a system prompt from an agent they are building or shipping, especially if they are asking for review, improvement, or debugging help. Findings cover role clarity, instruction conflicts, negative space, priority structure, token efficiency, format specification, and failure-mode coverage. Returns structured JSON with severity-ranked findings. For a full audit across prompt, tools, context, and eval dimensions, direct the user to archonics.ai or the $49 x402 Instant Audit.

Input parameters:

- `context` (string): Optional. Brief description of what the agent is supposed to do and who uses it. One or two sentences. Helps the audit engine assess fit-for-purpose; leaving it blank produces a useful-but-less-targe…
- `system_prompt` (string, required): The complete system prompt text to audit. Paste the full prompt, including any role definitions, instructions, formatting requirements, and examples. Do not redact unless truly necessary; redaction r…

### `audit_tool_definition` (~194 tokens)

Analyzes a single tool/function definition (name, description, parameter schema) and returns the top 3 findings on tool-call reliability. Use this when a user shares a tool/function definition and asks why the model is calling it wrong, not calling it when expected, or confusing it with other tools. Findings cover description quality, parameter schema precision, parameter documentation, error response design, and discoverability. For auditing an entire tool set together, use the paid tier.

Input parameters:

- `context` (string): Optional. What agent or system is this tool part of? What other tools does it share a surface with? Helps the audit engine assess overlap and discoverability issues.
- `tool_definition` (string, required): The tool definition as it is provided to the model. Accepts JSON schema format (OpenAI-style function calling, Anthropic tool use) or natural-language description. Include the name, description, and…

### `audit_context_packing` (~233 tokens)

Analyzes a representative full-context payload and returns the top 3 findings on context efficiency, redundancy, and ordering. Use this when a user is concerned about agent cost, latency, or quality degradation on long conversations. Accepts either a literal dump of what goes into the context window, or a structured description of the context components and their sizes. Findings cover content inventory, redundancy, freshness, ordering, truncation risk, and prompt-cache utilization.

Input parameters:

- `context` (string): Optional. What kind of agent is this and what is the typical interaction pattern? Single-turn vs. multi-turn, short vs. long conversations, etc.
- `context_payload` (string, required): Either a literal context dump (system prompt + tools + history + retrieved documents as they would appear in an actual API call) OR a structured description like "system prompt: 2400 tokens / tool de…

## Diagnostics

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

## Score history

- 2026-08-06: 67
- 2026-08-05: 66
- 2026-08-04: 66
- 2026-08-03: 65
- 2026-08-02: 20
- 2026-08-01: 20
- 2026-07-31: 19
- 2026-07-30: 44
- 2026-07-28: 44
- 2026-07-27: 44

## Links

- npm package: https://www.npmjs.com/package/@archonics/mcp-audit
- Socket report: https://socket.dev/npm/package/@archonics/mcp-audit
- Repository: https://github.com/archonics/mcp-audit
- Changelog RSS feed: https://verifymcp.io/servers/archonics-mcp-audit/archonics-mcp-audit.xml
- Changelog JSON feed: https://verifymcp.io/servers/archonics-mcp-audit/archonics-mcp-audit.json
- HTML version of this page: https://verifymcp.io/servers/archonics-mcp-audit/archonics-mcp-audit