# io.github.mythos-agent/mythos-agent (npm · mythos-agent)

Open-source AI security agent: SAST, DAST, and policy-as-code over MCP.

- Trust score: 71/100 (medium)
- Change this week: +25
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `mythos-agent`: 71/100 (this document), [markdown](https://verifymcp.io/servers/mythos-agent-mythos-agent/mythos-agent.md), [page](https://verifymcp.io/servers/mythos-agent-mythos-agent/mythos-agent)

## Channel facts

- Registry: `npm`
- Package: `mythos-agent`
- Version: `4.0.1`
- 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 (74 of 75), 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 (74 of 75), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to mythos-agent/mythos-agent).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 74 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 555 tokens (~46/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add mythos-agent-mythos-agent -- npx -y mythos-agent
```

### Codex

```bash
codex mcp add mythos-agent-mythos-agent -- npx -y mythos-agent
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add mythos-agent-mythos-agent --command npx --arg -y --arg mythos-agent
```

### Hermes

```yaml
mcp_servers:
  mythos-agent-mythos-agent:
    command: "npx"
    args: ["-y", "mythos-agent"]
```

### Other

```json
{
  "mcpServers": {
    "mythos-agent-mythos-agent": {
      "command": "npx",
      "args": [
        "-y",
        "mythos-agent"
      ]
    }
  }
}
```

## 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 71, +12)

- [security regression] Known CVEs: partial → unverified
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-08-01 (score 59, +38)

- [security improvement] Install scripts: unverified → pass
- [security improvement] Provenance: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [security] The attested source repository moved: mythos-agent/mythos-agent
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 21, −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 46)

First indexed and scored.

## MCP tools (12)

### `mythos_scan` (~59 tokens)

Scan a project for security vulnerabilities. Returns findings with severity, location, and description.

Input parameters:

- `path` (string): Project path to scan (default: current directory)
- `severity` (string): Minimum severity: critical, high, medium, low

### `sphinx_scan` (~70 tokens)

Scan a project for security vulnerabilities. Returns findings with severity, location, and description. (DEPRECATED legacy alias — use mythos_scan.)

Input parameters:

- `path` (string): Project path to scan (default: current directory)
- `severity` (string): Minimum severity: critical, high, medium, low

### `mythos_secrets` (~38 tokens)

Scan for hardcoded secrets, API keys, passwords, and tokens in source code.

Input parameters:

- `path` (string): Project path to scan

### `sphinx_secrets` (~50 tokens)

Scan for hardcoded secrets, API keys, passwords, and tokens in source code. (DEPRECATED legacy alias — use mythos_secrets.)

Input parameters:

- `path` (string): Project path to scan

### `mythos_endpoints` (~40 tokens)

Discover all API endpoints in the codebase and assess their security (auth status, risk level).

Input parameters:

- `path` (string): Project path to analyze

### `sphinx_endpoints` (~52 tokens)

Discover all API endpoints in the codebase and assess their security (auth status, risk level). (DEPRECATED legacy alias — use mythos_endpoints.)

Input parameters:

- `path` (string): Project path to analyze

### `mythos_iac` (~35 tokens)

Scan Docker, Terraform, and Kubernetes files for security misconfigurations.

Input parameters:

- `path` (string): Project path to scan

### `sphinx_iac` (~47 tokens)

Scan Docker, Terraform, and Kubernetes files for security misconfigurations. (DEPRECATED legacy alias — use mythos_iac.)

Input parameters:

- `path` (string): Project path to scan

### `mythos_results` (~37 tokens)

Get the latest scan results for a project. Returns all findings, chains, and trust score.

Input parameters:

- `path` (string): Project path

### `sphinx_results` (~48 tokens)

Get the latest scan results for a project. Returns all findings, chains, and trust score. (DEPRECATED legacy alias — use mythos_results.)

Input parameters:

- `path` (string): Project path

### `mythos_score` (~34 tokens)

Get a security score (0-100) with letter grade for the project.

Input parameters:

- `path` (string): Project path

### `sphinx_score` (~45 tokens)

Get a security score (0-100) with letter grade for the project. (DEPRECATED legacy alias — use mythos_score.)

Input parameters:

- `path` (string): Project path

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/mythos-agent-mythos-agent/mythos-agent#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 71
- 2026-08-01: 59
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

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