# SafeGrd (oci · ghcr.io/safegrd/cli)

Read backups and Fire Drills, and ask for a backup or a drill. No tool deletes a backup.

- Trust score: 39/100 (low)
- Change this week: +33
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `safegrd.dev`: 36/100, [markdown](https://verifymcp.io/servers/dev-safegrd-safegrd/safegrd.md), [page](https://verifymcp.io/servers/dev-safegrd-safegrd/safegrd)
- oci · `ghcr.io/safegrd/cli`: 39/100 (this document), [markdown](https://verifymcp.io/servers/dev-safegrd-safegrd/ghcr-io-safegrd-cli.md), [page](https://verifymcp.io/servers/dev-safegrd-safegrd/ghcr-io-safegrd-cli)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/safegrd/cli`
- Version: `0.0.29`
- 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 2026-10-18.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (BUSL-1.1) isn't a recognized OSI-approved license.
  - Actively maintained (last published 12 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 (good).
  - Tool/resource definitions use about 467 tokens (~66/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 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).

**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

### How do I install the SafeGrd MCP server?

SafeGrd runs locally as a container image, launched with docker run --rm -i ghcr.io/safegrd/cli:0.0.29. 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 dev-safegrd-safegrd -- docker run --rm -i ghcr.io/safegrd/cli:0.0.29
```

### Cursor

```json
{
  "mcpServers": {
    "dev-safegrd-safegrd": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/safegrd/cli:0.0.29"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-safegrd-safegrd": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/safegrd/cli:0.0.29"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dev-safegrd-safegrd -- docker run --rm -i ghcr.io/safegrd/cli:0.0.29
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-safegrd-safegrd": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/safegrd/cli:0.0.29"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  dev-safegrd-safegrd:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/safegrd/cli:0.0.29"]
```

### Netclaw

```json
{
  "McpServers": {
    "dev-safegrd-safegrd": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/safegrd/cli:0.0.29"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "dev-safegrd-safegrd": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/safegrd/cli:0.0.29"
      ]
    }
  }
}
```

## 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.

### 2026-10-18 (score 39, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 38, +1)

- [functional improvement] Stability: unverified → 0.10

### 2026-10-14 (score 37, +31)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-10-07 (score 6)

First indexed and scored.

## MCP tools (7)

### `backup` (~94 tokens)

Back up now

Back up now: one surface of this host's config by id (surface), the configured database, or a directory tree given as files. Take one before changing a database. The snapshot is encrypted and locked, and cannot be deleted early.

Input parameters:

- `files` (string): A directory tree to back up instead of the configured database.
- `surface` (string): The id of one surface in this host's config to back up now.

### `doctor` (~26 tokens)

Doctor

Check this host's configuration, key, storage and database access, and say what is wrong.

### `export` (~89 tokens)

Export snapshots

Copy every snapshot, still encrypted, to a directory (to_dir) or your own bucket (to_bucket). Nothing is decrypted or deleted.

Input parameters:

- `to_bucket` (string): Your own S3 bucket to copy every snapshot into, still encrypted.
- `to_dir` (string): A directory to copy every snapshot into, still encrypted.
- `to_endpoint` (string): The S3 endpoint of to_bucket.

### `list` (~28 tokens)

List snapshots

Every snapshot in this host's storage: when, what it holds, and until when it is locked.

### `restore` (~82 tokens)

Restore into an empty target

Restore a snapshot into a new or empty directory (target_dir) or an empty database (target_url). Never over existing data.

Input parameters:

- `snapshot_id` (string, required): Snapshot id, from the list tool.
- `target_dir` (string): A new or empty directory to restore files or mail into.
- `target_url` (string): An empty database URL to restore into.

### `status` (~21 tokens)

Status

This host's storage and remote server connection, and its latest snapshot.

### `verify` (~81 tokens)

Run a Fire Drill

Prove a snapshot restores (a Fire Drill): replayed in memory, or restored into sandbox_url, an empty database, for a full drill.

Input parameters:

- `sandbox_url` (string): An empty database to restore into for a full Fire Drill. Without it the snapshot is replayed in memory.
- `snapshot_id` (string, required): Snapshot id, from the list tool.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/dev-safegrd-safegrd/ghcr-io-safegrd-cli#diagnostics

## Score history

- 2026-10-18: 39
- 2026-10-17: 38
- 2026-10-16: 37
- 2026-10-15: 37
- 2026-10-14: 37
- 2026-10-13: 6
- 2026-10-12: 6
- 2026-10-10: 6
- 2026-10-07: 6

## Common questions

### What is the SafeGrd MCP server?

SafeGrd is an MCP server listed in the public MCP registry as dev.safegrd/safegrd. Read backups and Fire Drills, and ask for a backup or a drill. No tool deletes a backup. This page covers its container image (ghcr.io/safegrd/cli).

### Is the SafeGrd MCP server safe to use?

SafeGrd scores 39 out of 100 on VerifyMCP. 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 SafeGrd MCP server expose?

SafeGrd exposes 7 tools: backup, doctor, export, list, restore, and 2 more. Their descriptions and schemas cost roughly 421 tokens of context every time the server is loaded.

### Is the SafeGrd MCP server still maintained?

SafeGrd is still listed as active in the MCP registry. We last reached this channel on 18 October 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 SafeGrd MCP server under?

SafeGrd declares the BUSL-1.1 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/safegrd/cli
- Repository: https://github.com/safegrd/cli
- Website: https://safegrd.dev/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/dev-safegrd-safegrd/ghcr-io-safegrd-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-safegrd-safegrd/ghcr-io-safegrd-cli.json
- HTML version of this page: https://verifymcp.io/servers/dev-safegrd-safegrd/ghcr-io-safegrd-cli