# mcp-armor (oci · ghcr.io/studiomeyer-io/mcp-armor:0.7.0)

Security sidecar for MCP servers: prompt-injection scan, Ed25519 verify, tools/list drift. 10 tools.

- Trust score: 34/100 (low)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- oci · `ghcr.io/studiomeyer-io/mcp-armor:0.7.0`: 34/100 (this document), [markdown](https://verifymcp.io/servers/io-studiomeyer-armor/ghcr-io-studiomeyer-io-mcp-armor-0-7-0.md), [page](https://verifymcp.io/servers/io-studiomeyer-armor/ghcr-io-studiomeyer-io-mcp-armor-0-7-0)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/studiomeyer-io/mcp-armor:0.7.0`
- 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 2026-08-03.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - Install-script risk not yet assessed.
  - Dependency-health data not yet available.
- **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 65 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 544 tokens (~54/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 13% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); 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 io-studiomeyer-armor -- docker run --rm -i ghcr.io/studiomeyer-io/mcp-armor:0.7.0
```

### Codex

```bash
codex mcp add io-studiomeyer-armor -- docker run --rm -i ghcr.io/studiomeyer-io/mcp-armor:0.7.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-studiomeyer-armor": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/studiomeyer-io/mcp-armor:0.7.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  io-studiomeyer-armor:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/studiomeyer-io/mcp-armor:0.7.0"]
```

### Other

```json
{
  "mcpServers": {
    "io-studiomeyer-armor": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/studiomeyer-io/mcp-armor:0.7.0"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 34, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-01 (score 31, −3)

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

### 2026-07-28 (score 34, +23)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fair
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 13
- [functional] First check of Schema quality: fail

### 2026-07-26 (score 11)

First indexed and scored.

## MCP tools (10)

### `armor_scan_payload` (~33 tokens)

Scan an arbitrary payload for prompt-injection patterns.

Input parameters:

- `direction` (string, required)
- `payload` (string, required)

### `armor_verify_manifest` (~62 tokens)

Verify Ed25519 signature over canonical-JSON form of a tools/list response.

Input parameters:

- `public_key_b64` (string, required)
- `signature_b64` (string, required)
- `signed_at_iso` (string)
- `tools_list_response` (object, required)

### `armor_list_blocked` (~37 tokens)

Read recent blocked tool calls from the in-memory ring buffer.

Input parameters:

- `limit` (integer)
- `since_iso` (string)

### `armor_get_policy` (~27 tokens)

Return the active policy: file path, rules, fail mode, scan flags, version.

### `armor_check_cve` (~42 tokens)

Look up a server name in the curated CVE feed and return affected entries.

Input parameters:

- `server_name` (string, required)
- `server_version` (string)

### `armor_simulate_attack` (~39 tokens)

Run the static simulate_payload for a CVE through the scanner. Never spawns the upstream binary.

Input parameters:

- `cve_id` (string, required)

### `armor_get_keystore` (~63 tokens)

v0.2 — List pinned TOFU maintainer public keys (server_name + fingerprint + pinned_at_iso). Read-only inspection of the keystore configured at sidecar startup (no caller-supplied path — operator-only via `--keystore` flag).

### `armor_verify_bundle` (~44 tokens)

v0.2 — Parse a cosign sigstore.json bundle and structurally verify the Rekor SignedEntryTimestamp shape. Offline.

Input parameters:

- `bundle_json` (string, required)

### `armor_rekor_lookup` (~78 tokens)

v0.2 — Query the Sigstore Rekor transparency log for inclusion of a manifest's artifact hash. Requires --features sigstore-bridge at build time. Network call.

Input parameters:

- `rekor_url` (string): Override Rekor endpoint; defaults to https://rekor.sigstore.dev
- `tools_list_response` (object, required)

### `armor_get_drift_history` (~119 tokens)

v0.5 Layer 7 — Inspect the tools-list schema-drift baselines persisted by `mcp-armor wrap`. Read-only. Optional `program` arg narrows the report to one upstream; omit it to list every pinned baseline. Closes the Rug-Pull / Silent-Redefinition threat class (Invariant Labs, CyberArk Full-Schema Poisoning).

Input parameters:

- `program` (string): When set, return the full per-tool fingerprint detail for one program. When omitted, return a summary list of every pinned baseline.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/io-studiomeyer-armor/ghcr-io-studiomeyer-io-mcp-armor-0-7-0#diagnostics

## Score history

- 2026-08-03: 34
- 2026-08-02: 31
- 2026-08-01: 31
- 2026-07-30: 34
- 2026-07-28: 34
- 2026-07-26: 11

## Links

- Repository: https://github.com/studiomeyer-io/mcp-armor
- Changelog RSS feed: https://verifymcp.io/servers/io-studiomeyer-armor/ghcr-io-studiomeyer-io-mcp-armor-0-7-0/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-studiomeyer-armor/ghcr-io-studiomeyer-io-mcp-armor-0-7-0/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-studiomeyer-armor/ghcr-io-studiomeyer-io-mcp-armor-0-7-0