Skip to main content
Glama
enesjakozh
jakenuts

mcp-cli-exec MCP Server

by jakenuts
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mcp-cli-exec MCP サーバー

強力なCLIコマンド実行MCPサーバー。構造化された出力を持つシェルコマンドの実行を可能にします。このパッケージはコマンド実行機能に特化しており、他のMCP CLIツールとは一線を画しています。

特徴

ツール

cli-exec-raw

生の CLI コマンドを実行し、構造化された出力を返す

  • コマンド文字列とオプションのタイムアウト（デフォルト: 5 分）を受け取ります。

  • stdout、stderr、終了コードを含む詳細な実行結果を返します。

  • 構造化されたエラー応答でエラーを適切に処理します

cli-exec

特定の作業ディレクトリで1つ以上のCLIコマンドを実行する

  • 単一コマンド、&& 連鎖コマンド、またはコマンドの配列をサポートします

  • すべてのコマンドは指定された作業ディレクトリで実行されます

  • 各コマンドの詳細な結果を返します。

    • 成功/失敗ステータス

    • 終了コード

    • stdout と stderr (ANSI コードは削除)

    • 実行期間

    • 作業ディレクトリ

  • 最初のコマンドが失敗すると停止します

  • コマンドごとのオプションのタイムアウト（デフォルト: 5 分）

注: 実行コンテキストの制限により、各コマンドは独立して実行されます。コマンド内でのディレクトリ変更（cd）は、後続のコマンドには影響しません。すべてのコマンドは、最初に指定された作業ディレクトリで実行されます。

出力形式

コマンドは次のような構造化された結果を返します:

  • 成功/失敗ステータス

  • 終了コード

  • stdout と stderr (ANSI コードは削除)

  • 実行期間

  • 作業ディレクトリ

  • 詳細なエラー情報（該当する場合）

使用例

cli-exec-raw

簡単なコマンド実行:

{
  "command": "echo Hello World"
}

タイムアウトあり:

{
  "command": "long-running-script.sh",
  "timeout": 300000
}

cli-exec

特定のディレクトリ内の単一コマンド:

{
  "workingDirectory": "/path/to/project",
  "commands": "npm install"
}

複数のコマンド (すべて同じ作業ディレクトリで実行):

{
  "workingDirectory": "C:\\project",
  "commands": [
    "dir /b",
    "npm run build"
  ]
}

Related MCP server: MCP Server

インストール

オプションでnpmからインストールします:

npm install -g mcp-cli-exec
# or with pnpm
pnpm add -g mcp-cli-exec

または、設定でnpxを使用するだけです

Cline VSCode拡張機能

%APPDATA%/Code - Insiders/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.jsonに追加します:

{
  "mcpServers": {
    "mcp-cli-exec": {
      "command": "npx",
      "args": ["-y", "mcp-cli-exec"]
    }
  }
}

クロードデスクトップ向け

適切な設定ファイルに追加します:

Windows: %APPDATA%/Claude/claude_desktop_config.json MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-cli-exec": {
      "command": "npx",
      "args": ["-y", "mcp-cli-exec"]
    }
  }
}

特別なWindows構成

Windows で ENOENT spawn npx の問題が発生した場合は、完全なパスを指定する次の代替構成を使用します。

{
  "mcpServers": {
    "mcp-cli-exec": {
      "command": "C:\\Users\\jim\\AppData\\Roaming\\nvm\\v22.1.0\\node.exe",
      "args": [
        "C:\\Users\\jim\\AppData\\Roaming\\npm\\node_modules\\npm\\bin\\npx-cli.js",
        "-y",
        "mcp-cli-exec"
      ]
    }
  }
}

発達

依存関係をインストールします:

pnpm install

サーバーを構築します。

pnpm run build

自動リビルドを使用した開発の場合:

pnpm run watch

デバッグ

MCPサーバーはstdio経由で通信するため、デバッグが困難になる場合があります。MCP Inspectorは便利なデバッグツールを提供します。

pnpm run inspector

これにより、ブラウザでインスペクタにアクセスするための URL が提供され、次の操作を実行できます。

  • すべてのMCPメッセージを表示

  • リクエスト/レスポンスペイロードを検査する

  • ツールをインタラクティブにテストする

  • サーバーの状態を監視する

エラー処理

サーバーには包括的なエラー処理が含まれています。

  • すべてのツールパラメータの入力検証

  • 構造化されたエラー応答

  • コマンドタイムアウト処理

  • 作業ディレクトリの検証

  • きれいな出力のための ANSI コード除去

技術的な詳細

  • TypeScriptとMCP SDKを使用して構築

  • 信頼性の高いコマンド実行のためにexecaを使用する

  • デフォルトのコマンドタイムアウト: 5分

  • Windows および Unix 系システムをサポートします (OS に応じて適切なコマンドを使用します (例: 'dir' と 'ls'))

  • コマンドを順番に実行し、最初の失敗で停止します

  • 各コマンドは指定された作業ディレクトリ内で独立して実行されます

Available Tools

2 tools
cli-execC

Execute one or more CLI commands in a specific working directory

ParametersJSON Schema
NameRequiredDescriptionDefault
commandsYesCommands to execute
timeoutNoOptional timeout in milliseconds per command (default: 5 minutes)
workingDirectoryYesWorking directory to execute commands in

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states basic functionality. It doesn't disclose critical behavioral traits like execution safety (potential for destructive commands), authentication needs, error handling, output format, or rate limits. The mention of 'timeout' in the schema isn't reinforced in the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. Every element ('Execute', 'CLI commands', 'specific working directory') earns its place, making it optimally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a CLI execution tool with no annotations and no output schema, the description is insufficient. It lacks details on execution behavior (e.g., sequential vs. parallel), error propagation, security implications, or return values, leaving significant gaps for an agent to understand tool usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all parameters. The description adds no additional parameter semantics beyond what's in the schema, maintaining the baseline score of 3 for adequate coverage through structured data alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Execute') and resource ('CLI commands') with additional context about working directory. It distinguishes from sibling 'cli-exec-raw' by specifying 'in a specific working directory', though the distinction isn't fully explicit about what makes the sibling different.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus the sibling 'cli-exec-raw'. It mentions the working directory context but doesn't explain alternative scenarios, prerequisites, or exclusions for tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

cli-exec-rawC

Execute a raw CLI command and return structured output

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesThe CLI command to execute
timeoutNoOptional timeout in milliseconds (default: 5 minutes)

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool executes commands and returns structured output, but fails to address critical behavioral aspects such as security implications, execution environment, error handling, or potential side effects. This is inadequate for a tool that executes arbitrary CLI commands.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and front-loaded in a single sentence that captures the core functionality. Every word earns its place with no wasted text, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of executing arbitrary CLI commands (which involves security, environment, and side-effect considerations), no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what 'structured output' means, execution constraints, or safety warnings, leaving significant gaps for agent understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with clear parameter descriptions in the schema. The description adds no additional parameter semantics beyond what the schema provides, such as command syntax examples or timeout behavior details. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Execute a raw CLI command and return structured output'. It specifies the verb ('execute'), resource ('raw CLI command'), and outcome ('return structured output'). However, it doesn't explicitly differentiate from its sibling 'cli-exec', which likely has similar functionality, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus its sibling 'cli-exec' or other alternatives. It lacks context about appropriate use cases, prerequisites, or exclusions, leaving the agent with minimal direction beyond the basic purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observedcli-exec
    • First observedcli-exec-raw
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.9/5.0

Scored across 2 tools

Disambiguation2/5

The two tools have significant overlap in purpose, both executing CLI commands. While cli-exec-raw specifies 'raw' and 'structured output', the distinction is subtle and could easily lead to confusion about which to use for basic command execution. The descriptions don't clearly delineate when to choose one over the other.

Naming Consistency4/5

Both tools follow a consistent cli-exec prefix pattern with hyphenated suffixes. The naming is predictable and readable, though the suffix conventions differ slightly (one has no suffix, the other uses '-raw'). This minor deviation keeps it from a perfect score.

Tool Count3/5

With only 2 tools, the server feels thin for a CLI execution domain. While it covers basic execution, more operations like command validation, history tracking, or batch processing might be expected. The count is borderline minimal but functional for core tasks.

Completeness2/5

For a CLI execution server, there are notable gaps. Missing tools for command chaining, environment variable management, output parsing beyond 'structured', or error handling make the surface incomplete. Agents will hit dead ends when needing advanced CLI interactions beyond simple execution.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Shell MCP Server

    odysseus0
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that allows LLMs to execute shell commands and receive their output in a controlled manner.
    7
    MIT

  • MCP Server

    mokemoke0821
    A
    license
    Not graded
    quality
    D
    maintenance
    A cross-platform shell command execution server that supports Windows, macOS, and Linux environments with PowerShell, CMD, GitBash, and Bash shells, optimized for Japanese language environments.
    48 npm
    MIT

  • mcp2term

    FreddyE1982
    F
    license
    B
    quality
    D
    maintenance
    Enables safe execution of system shell commands with real-time streaming output and rich metadata capture. Provides configurable command execution with timeout controls, environment management, and extensible plugin architecture for monitoring command lifecycles.
    4
    -

  • MCP Terminal Tool Server

    gkgaurav31
    F
    license
    B
    quality
    D
    maintenance
    An MCP server that enables users to execute arbitrary shell commands on their local machine and receive the output. It provides a terminal tool for running system commands through MCP-compatible clients using the Python SDK.
    1
    -

Appeared in Searches