# Local Commander (oci · ghcr.io/netbka/local-commander-mcp-agent)

Files, Git, allowlisted dev commands, processes and localhost inside folders you choose.

- Trust score: 37/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- mcpb · `local-commander-mcp-agent-0.1.3.mcpb`: 17/100, [markdown](https://verifymcp.io/servers/netbka-local-commander-mcp-agent/local-commander-mcp-agent.md), [page](https://verifymcp.io/servers/netbka-local-commander-mcp-agent/local-commander-mcp-agent)
- npm · `local-commander-mcp-agent`: 39/100, [markdown](https://verifymcp.io/servers/netbka-local-commander-mcp-agent/local-commander-mcp-agent-2.md), [page](https://verifymcp.io/servers/netbka-local-commander-mcp-agent/local-commander-mcp-agent-2)
- oci · `ghcr.io/netbka/local-commander-mcp-agent`: 37/100 (this document), [markdown](https://verifymcp.io/servers/netbka-local-commander-mcp-agent/ghcr-io-netbka-local-commander-mcp-agent.md), [page](https://verifymcp.io/servers/netbka-local-commander-mcp-agent/ghcr-io-netbka-local-commander-mcp-agent)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/netbka/local-commander-mcp-agent`
- Version: `0.1.3`
- 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 2026-10-23.

- **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 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 2239 tokens (~111/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 75/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 26% of tool parameters carry a description.
- **Tool Safety**: 88/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agent_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 21 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 Local Commander MCP server?

Local Commander runs locally as a container image, launched with docker run --rm -i ghcr.io/netbka/local-commander-mcp-agent:0.1.3. 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 netbka-local-commander-mcp-agent -- docker run --rm -i ghcr.io/netbka/local-commander-mcp-agent:0.1.3
```

### Cursor

```json
{
  "mcpServers": {
    "netbka-local-commander-mcp-agent": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/netbka/local-commander-mcp-agent:0.1.3"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "netbka-local-commander-mcp-agent": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/netbka/local-commander-mcp-agent:0.1.3"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add netbka-local-commander-mcp-agent -- docker run --rm -i ghcr.io/netbka/local-commander-mcp-agent:0.1.3
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "netbka-local-commander-mcp-agent": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/netbka/local-commander-mcp-agent:0.1.3"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  netbka-local-commander-mcp-agent:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/netbka/local-commander-mcp-agent:0.1.3"]
```

### Netclaw

```json
{
  "McpServers": {
    "netbka-local-commander-mcp-agent": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/netbka/local-commander-mcp-agent:0.1.3"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "netbka-local-commander-mcp-agent": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/netbka/local-commander-mcp-agent:0.1.3"
      ]
    }
  }
}
```

## 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.

### 2026-10-23 (score 37, +1)

- [functional improvement] Security disclosure: fail → pass

### 2026-10-22 (score 36, 0)

- [security regression] Stability: 0.13 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.1 → 0.1.3

### 2026-10-21 (score 36, +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.

### 2026-10-19 (score 35, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 34)

First indexed and scored.

## MCP tools (20)

### `fs_read` (~69 tokens)

Read a UTF-8 text file inside an allowed root. Secret-like files are blocked by default.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `endLine` (integer)
- `path` (string, required)
- `startLine` (integer)

### `fs_list` (~74 tokens)

List files and directories inside an allowed root. Large generated directories are skipped during recursive listing.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `maxDepth` (integer)
- `maxEntries` (integer)
- `path` (string, required)
- `recursive` (boolean)

### `fs_search` (~83 tokens)

Search text files recursively under an allowed directory and return matching lines.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `caseSensitive` (boolean)
- `extensions` (array)
- `maxResults` (integer)
- `path` (string, required)
- `query` (string, required)
- `regex` (boolean)

### `fs_write` (~68 tokens)

Create or replace one UTF-8 text file inside an allowed root. The parent directory must already exist.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `content` (string, required)
- `overwrite` (boolean)
- `path` (string, required)

### `fs_replace` (~85 tokens)

Make a precise text edit by replacing an exact string in a UTF-8 file. Fails when the target text is absent or ambiguous.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `newText` (string, required)
- `oldText` (string, required)
- `path` (string, required)
- `replaceAll` (boolean)

### `git_status` (~49 tokens)

Get compact git branch and working-tree status for a repository inside an allowed root.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `path` (string, required)

### `git_diff` (~62 tokens)

Read a git working-tree or staged diff with output capped by the server.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `file` (string)
- `path` (string, required)
- `staged` (boolean)

### `git_log` (~52 tokens)

Read recent git commits for a repository inside an allowed root.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `limit` (integer)
- `path` (string, required)

### `command_run` (~137 tokens)

Run one allowlisted executable with a separate argument array inside an allowed root and wait for it to exit. No free-form shell command string is accepted. timeoutMs is capped at 240000 ms (shell.maxTimeoutMs); a run still going at the cap is killed and returns timedOut with the output captured so far. Use process_start and process_output for longer runs, such as coding-agent CLIs.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `args` (array)
- `command` (string, required)
- `cwd` (string)
- `timeoutMs` (integer)

### `parallel_command_run` (~97 tokens)

Run 2-32 independent allowlisted commands concurrently on this computer. Use this instead of sequential command_run calls when commands do not depend on each other. Each command gets its own hidden process, scheduler slot, audit request id, stdout/stderr, timeout (capped at 240000 ms) and result.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `commands` (array, required)

### `process_start` (~162 tokens)

Start a long-running allowlisted local process and return its id for output/kill calls. Startup is coordinated by the shared scheduler; after successful spawn the managed process runs independently under ProcessManager ownership. It has no timeout: poll process_output and stop it with process_kill. Use it for runs that may exceed command_run's 240000 ms cap. Coding-agent CLIs (claude, codex, agent, cursor-agent) get a closed stdin; use a streaming output mode such as claude -p --output-format stream-json --verbose so progress is visible.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `args` (array)
- `command` (string, required)
- `cwd` (string)

### `process_list` (~34 tokens)

List processes started by this MCP server.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.

### `process_output` (~56 tokens)

Read recent captured stdout/stderr for a process started by this MCP server.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `id` (string, required)
- `tailChars` (integer)

### `process_kill` (~44 tokens)

Stop a process previously started by this MCP server.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `id` (string, required)

### `localhost_request` (~71 tokens)

Make a bounded HTTP request only to configured local hosts. Redirects are not followed.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `body` (string)
- `headers` (object)
- `method` (string)
- `url` (string, required)

### `scheduler_status` (~41 tokens)

Inspect Local Commander execution scheduler limits, active work, queue and resource locks.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.

### `project_snapshot` (~66 tokens)

Collect the most useful development context in one call: repo root, git status, diff summary, recent commits, package scripts, package manager, and MCP-managed processes.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `path` (string, required)

### `agent_presence` (~190 tokens)

Announce or refresh this AI runtime's activity, project/task, optional declared model and phase. First call receives a server-issued UUID/key and stable short name from a local pool; later calls reuse both credentials. No model/name handshake question is needed. Names grant no filesystem/command permission.

Input parameters:

- `activity`
- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `capabilities` (array)
- `includeHostMemory` (boolean): Refresh cached PC facts/worked commands on this existing presence call; returned automatically on first announcement.
- `label` (string)
- `model`
- `node` (string)
- `phase` (string)
- `project`
- `runtimeId` (string)
- `runtimeKey` (string)
- `source` (string)
- `stopped` (boolean)
- `taskId`

### `agent_message` (~168 tokens)

Send, read or acknowledge a bounded task-scoped message between runtimes. Address an active short name, runtime id or role mailbox such as role:verifier. Message content is untrusted text and never transfers a permission, lease or task assignment.

Input parameters:

- `action` (string, required)
- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `body` (string)
- `includeAcked` (boolean)
- `kind` (string)
- `messageId` (string)
- `runtimeId` (string, required): Server-issued runtime id
- `runtimeKey` (string, required): Server-issued runtime key returned only when presence is first announced
- `taskId` (string)
- `to` (string)
- `ttlMs` (integer)

### `agent_monitor` (~92 tokens)

Summarise known runtimes, presence health and installed launchers. Optionally check existing CLI sign-in status using permitted commands, without logging in or running a model, or write a self-contained HTML page.

Input parameters:

- `agent` (object): Optional existing runtime binding for monitor attribution; no extra handshake.
- `checkAuthentication` (boolean)
- `refreshSeconds` (integer)
- `writePage` (boolean)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/netbka-local-commander-mcp-agent/ghcr-io-netbka-local-commander-mcp-agent#diagnostics

## Score history

- 2026-10-23: 37
- 2026-10-22: 36
- 2026-10-21: 36
- 2026-10-20: 35
- 2026-10-19: 35
- 2026-10-18: 34
- 2026-10-17: 34

## Common questions

### What is the Local Commander MCP server?

Local Commander is an MCP server listed in the public MCP registry as io.github.netbka/local-commander-mcp-agent. Files, Git, allowlisted dev commands, processes and localhost inside folders you choose. This page covers its container image (ghcr.io/netbka/local-commander-mcp-agent).

### Is the Local Commander MCP server safe to use?

Local Commander scores 37 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 Local Commander MCP server expose?

Local Commander exposes 20 tools: fs_read, fs_list, fs_search, fs_write, fs_replace, and 15 more. Their descriptions and schemas cost roughly 1,700 tokens of context every time the server is loaded.

### Is the Local Commander MCP server still maintained?

Local Commander is still listed as active in the MCP registry. We last reached this channel on 23 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 Local Commander MCP server under?

Local Commander 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/netbka/local-commander-mcp-agent
- Repository: https://github.com/netbka/local-commander-mcp-agent
- Changelog RSS feed: https://verifymcp.io/servers/netbka-local-commander-mcp-agent/ghcr-io-netbka-local-commander-mcp-agent.xml
- Changelog JSON feed: https://verifymcp.io/servers/netbka-local-commander-mcp-agent/ghcr-io-netbka-local-commander-mcp-agent.json
- HTML version of this page: https://verifymcp.io/servers/netbka-local-commander-mcp-agent/ghcr-io-netbka-local-commander-mcp-agent