# io.github.SoWhatI/vaultshell (oci · ghcr.io/sowhati/vaultshell)

Injects secrets into shell commands at exec time; plaintext never reaches the LLM context

- Trust score: 50/100 (low)
- Change this week: −2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- oci · `ghcr.io/sowhati/vaultshell`: 50/100 (this document), [markdown](https://verifymcp.io/servers/sowhati-vaultshell/ghcr-io-sowhati-vaultshell.md), [page](https://verifymcp.io/servers/sowhati-vaultshell/ghcr-io-sowhati-vaultshell)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/sowhati/vaultshell`
- Version: `0.1.2`
- 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 2026-11-05.

- **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**: 48/100
  - 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 35 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 917 tokens (~57/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 65% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "shell_exec" implies "exec" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **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

### How do I install the io.github.SoWhatI/vaultshell MCP server?

io.github.SoWhatI/vaultshell runs locally as a container image, launched with docker run --rm -i ghcr.io/sowhati/vaultshell:0.1.2. 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 sowhati-vaultshell -- docker run --rm -i ghcr.io/sowhati/vaultshell:0.1.2
```

### Cursor

```json
{
  "mcpServers": {
    "sowhati-vaultshell": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/sowhati/vaultshell:0.1.2"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sowhati-vaultshell": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/sowhati/vaultshell:0.1.2"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add sowhati-vaultshell -- docker run --rm -i ghcr.io/sowhati/vaultshell:0.1.2
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sowhati-vaultshell": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/sowhati/vaultshell:0.1.2"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  sowhati-vaultshell:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/sowhati/vaultshell:0.1.2"]
```

### Netclaw

```json
{
  "McpServers": {
    "sowhati-vaultshell": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/sowhati/vaultshell:0.1.2"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "sowhati-vaultshell": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/sowhati/vaultshell:0.1.2"
      ]
    }
  }
}
```

## 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.

### 2026-11-05 (score 50, −3)

- [functional] Stability: pass → 0.83

### 2026-11-04 (score 53, +1)

- [functional improvement] Security disclosure: unverified → pass

### 2026-11-03 (score 52, −1)

- [functional regression] Security disclosure: pass → unverified

### 2026-10-30 (score 53, +1)

- [security] Stability: 0.97 → pass

### 2026-10-28 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 51, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 50, 0)

- [security regression] Provenance: unverified → fail

### 2026-10-24 (score 50, 0)

- [security regression] Provenance: fail → unverified

## MCP tools (16)

### `shell_exec` (~140 tokens)

Execute a one-shot shell command with secrets injected per matching rule. Output is redacted: injected secret values never appear in the response. Dangerous commands (env, printenv, export -p, /proc/*/environ, ...) are hard-blocked. There is no free-form env parameter; secrets are only injected by reference via rules.

Input parameters:

- `command` (string, required): shell command to execute
- `cwd` (string): working directory (~ is expanded); default: server cwd
- `extraEnv` (object): non-secret env vars, keys must be in defaults.extraEnvAllowlist
- `profile` (string): optional profile name for rule matching

### `secret_list` (~26 tokens)

List registered secret names with metadata (backend ref, resolvable). Never returns values.

### `secret_set` (~93 tokens)

Store a secret value into the configured backend. The value is persisted, never echoed back, and the name is registered in rules.yaml (ref only).

Input parameters:

- `name` (string, required): secret name, e.g. PROD_DB_URL
- `ref` (string): optional explicit ref, e.g. keychain://svc/account; default: configured backend
- `value` (string, required): secret value; stored only, never returned

### `secret_delete` (~28 tokens)

Delete a secret from the backend and unregister it from rules.yaml.

Input parameters:

- `name` (string, required)

### `secret_probe` (~44 tokens)

Check whether a secret ref can be resolved. Returns only {ok, masked}; masked never contains value fragments unless defaults.maskTail > 0.

Input parameters:

- `name` (string, required)

### `rule_list` (~28 tokens)

List injection rules with static warnings (e.g. rules matching every directory → potential unintended full injection).

### `audit_query` (~42 tokens)

Query recent audit entries (newest last). Entries contain names and redacted commands only, never values.

Input parameters:

- `limit` (integer): max entries, default 50

### `shell_session_open` (~109 tokens)

Open a persistent shell session (PTY when node-pty is available, plain child_process otherwise — the response's `pty` field says which). Secrets are injected once at creation per matching rule; idle sessions are killed after ttlSeconds (rule ttlSeconds overrides defaults.sessionTtlSeconds).

Input parameters:

- `cwd` (string): working directory (~ is expanded); default: server cwd
- `profile` (string): optional profile name for rule matching
- `ttlSeconds` (integer): idle TTL override (seconds)

### `shell_session_send` (~63 tokens)

Send a command to a persistent session. Output (merged stdout/stderr) is redacted before returning. Dangerous commands are blocked per security.dangerousCommands. Returns {output, exitCode}.

Input parameters:

- `command` (string, required)
- `sessionId` (string, required)

### `shell_session_close` (~31 tokens)

Close a session: kill the process; injected secrets die with it.

Input parameters:

- `sessionId` (string, required)

### `shell_session_list` (~30 tokens)

List live sessions (metadata only: id, cwd, injected names, pty, ttl, timestamps).

### `shell_session_revoke` (~47 tokens)

Immediately kill a session and rebuild a fresh one WITHOUT any injected secrets. Use when a session may have been compromised. Returns the new sessionId.

Input parameters:

- `sessionId` (string, required)

### `rule_validate` (~50 tokens)

Statically validate rules.yaml and return findings: unknown secret refs, unreachable rules (shadowed by earlier ones), inject-everywhere rules (high severity), requireConfirm capability notes, union mergeStrategy risk notes.

### `shell_proxy_start` (~127 tokens)

Start a credential-injecting reverse proxy on 127.0.0.1 (random port) for a `proxies` entry in config.yaml. Point commands at http://127.0.0.1:<port> instead of the real API host; the proxy injects the secret into the configured header in memory only. Auto-stops after its TTL (default defaults.proxyTtlSeconds=300s). The secret value is never returned anywhere.

Input parameters:

- `id` (string, required): proxies entry id from config.yaml
- `ttlSeconds` (integer): TTL override (seconds)

### `shell_proxy_stop` (~23 tokens)

Stop a running credential proxy.

Input parameters:

- `proxyId` (string, required)

### `shell_proxy_list` (~36 tokens)

List running credential proxies (metadata only: id, port, upstreamHost, secret NAME, expiry, request count). Never includes values.

## Diagnostics

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

## Score history

- 2026-11-05: 50
- 2026-11-04: 53
- 2026-11-03: 52
- 2026-11-02: 53
- 2026-11-01: 53
- 2026-10-31: 53
- 2026-10-30: 53
- 2026-10-29: 52
- 2026-10-28: 52
- 2026-10-27: 51
- 2026-10-26: 51
- 2026-10-25: 50
- 2026-10-24: 50
- 2026-10-23: 50
- 2026-10-22: 49
- 2026-10-21: 49
- 2026-10-20: 48
- 2026-10-19: 48
- 2026-10-18: 47
- 2026-10-17: 47
- 2026-10-16: 46
- 2026-10-15: 46
- 2026-10-14: 45
- 2026-10-13: 45
- 2026-10-12: 44
- 2026-10-10: 39
- 2026-10-05: 39
- 2026-10-04: 39
- 2026-10-03: 39
- 2026-10-02: 39

## Common questions

### What is the io.github.SoWhatI/vaultshell MCP server?

io.github.SoWhatI/vaultshell is an MCP server listed in the public MCP registry as io.github.SoWhatI/vaultshell. Injects secrets into shell commands at exec time; plaintext never reaches the LLM context. This page covers its container image (ghcr.io/sowhati/vaultshell).

### Is the io.github.SoWhatI/vaultshell MCP server safe to use?

io.github.SoWhatI/vaultshell scores 50 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 io.github.SoWhatI/vaultshell MCP server expose?

io.github.SoWhatI/vaultshell exposes 16 tools: shell_exec, secret_list, secret_set, secret_delete, secret_probe, and 11 more. Their descriptions and schemas cost roughly 917 tokens of context every time the server is loaded.

### Is the io.github.SoWhatI/vaultshell MCP server still maintained?

io.github.SoWhatI/vaultshell is still listed as active in the MCP registry. We last reached this channel on 5 November 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 io.github.SoWhatI/vaultshell MCP server under?

io.github.SoWhatI/vaultshell declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/sowhati/vaultshell
- Repository: https://github.com/SoWhatI/vaultshell
- Changelog RSS feed: https://verifymcp.io/servers/sowhati-vaultshell/ghcr-io-sowhati-vaultshell.xml
- Changelog JSON feed: https://verifymcp.io/servers/sowhati-vaultshell/ghcr-io-sowhati-vaultshell.json
- HTML version of this page: https://verifymcp.io/servers/sowhati-vaultshell/ghcr-io-sowhati-vaultshell