Skip to main content
Glama
enesjakozh
formulahendry

mcp-server-code-runner

by formulahendry
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

コードランナーMCPサーバー

NPMダウンロード 鍛冶屋のバッジ Dockerプル

コード スニペットを実行し、結果を表示するための MCP サーバー。

複数のプログラミング言語の実行をサポートしています： JavaScript、PHP、Python、Perl、Perl 6、Ruby、Go、Lua、Groovy、PowerShell、BAT/CMD、BASH/SH、F# Script、C# Script、VBScript、TypeScript、CoffeeScript、Scala、Swift、Julia、Crystal、OCaml Script、R、AppleScript、Elixir、Clojure、Racket、Scheme、AutoHotkey、AutoIt、Kotlin Script、Dart、Haskell、Ni、Lisp、Kit、V、SCSS、Sass 。全リストはconstants.tsで確認できます。

設定

VS Code 用の npx

以下のボタンを使用して、VS Code に Code Runner MCP サーバーをインストールします。

VS Codeにインストール VS Code Insiders にインストール

あるいは、 settings.jsonに構成を追加することもできます。

{
  "mcp": {
    "inputs": [],
    "servers": {
      "mcp-server-code-runner": {
        "command": "npx",
        "args": [
          "-y",
          "mcp-server-code-runner@latest"
        ],
      }
    }
  }
}

Claude デスクトップ用の npx

claude_desktop_config.json内の構成:

{
  "mcpServers": {
    "mcp-server-code-runner": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-code-runner@latest"
      ],
    }
  }
}

ドッカー

例としてVS Codeを使用します。以下のボタンを使用して、VS CodeにCode Runner MCPサーバーをインストールします。

VS Codeにインストール VS Code Insiders にインストール

あるいは、 settings.jsonに構成を追加することもできます。

{
  "mcp": {
    "inputs": [],
    "servers": {
      "mcp-server-code-runner": {
        "command": "docker",
        "args": [
          "run",
          "--rm",
          "-i",
          "formulahendry/mcp-server-code-runner"
        ]
      }
    }
  }
}

Windows の npx の問題

Windows では、 MCP サーバーがnpxに接続できない場合があります。

以下の 2 つの回避策を試すことができます。

bunxを使用する

  1. Bunをインストールします。

  2. 設定では、 npx``bunxに変更します。

cmdを使用する

以下は、 settings.jsonの VS Code 構成です。

{
  "mcp": {
    "inputs": [],
    "servers": {
      "mcp-server-code-runner": {
        "command": "cmd",
        "args": [
          "/c",
          "npx",
          "-y",
          "mcp-server-code-runner@latest"
        ],
      }
    }
  }
}

Related MCP server: MCP Expr Lang

ストリーミング可能なHTTPトランスポートで実行

npm install -g mcp-server-code-runner@latest
mcp-server-code-runner --transport http

使用法

Code Runner MCP Server を使用する前に、実行するプログラミング言語のインタープリターまたはコンパイラがPATH環境変数に設定されていることを確認してください。

Code Runner MCP Server が構成されているアプリケーションで以下のプロンプトを試してください。

  • Run the JavaScript Code: console.log(5+6)

  • Where is temporary folder in my OS? Use run-code tool

  • How many CPUs do I have in my machine? Use run-code tool

独自のMCPサーバーを構築する

独自の MCP サーバーを構築したいですか? MCP サーバー用の Yeoman Generatorを使用して、MCP サーバー プロジェクトを作成してみてください。

Available Tools

1 tool
run-codeC

Run code snippet and return the result.

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesCode Snippet
languageIdYesLanguage ID

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions running code and returning results but lacks critical details like execution environment, security implications, timeout limits, error handling, or resource constraints, which are essential for safe and effective use.

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. It is appropriately sized for the tool's function, making it highly concise and well-structured.

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 code execution (which involves security, performance, and error handling), the description is insufficient. With no annotations, no output schema, and minimal behavioral details, it fails to provide complete context for safe and informed use, especially for a tool that could have significant side effects.

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?

The description does not add meaning beyond the input schema, which has 100% coverage with clear descriptions for both parameters (code and languageId). Since the schema fully documents the parameters, the baseline score of 3 is appropriate, as the description provides no additional semantic context.

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 'Run code snippet and return the result' clearly states the action (run) and resource (code snippet) with a specific outcome (return result). It distinguishes the tool's function effectively, though it lacks sibling differentiation since no sibling tools exist, making a 5 unnecessary.

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, such as for testing, debugging, or specific contexts, and offers no alternatives or exclusions. It only states what the tool does without usage context, leaving the agent to infer applicability.

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. 1 tool update
    • First observedrun-code
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

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'run-code' has a clearly distinct and singular purpose.

Naming Consistency5/5

The single tool name 'run-code' follows a clear verb_noun pattern. Since there is only one tool, consistency is inherently perfect with no deviations.

Tool Count2/5

A single tool for a code runner server feels thin and limited in scope. It suggests the server may not fully cover the domain, as typical code execution might benefit from additional tools like listing environments or managing sessions.

Completeness2/5

The tool surface is severely incomplete for a code runner domain. It only provides execution without supporting operations like listing available languages, checking code syntax, or managing execution environments, which are common in such contexts.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches