標準化されたインターフェースを通じてファイル システム操作を提供するモデル コンテキスト プロトコル (MCP) サーバー実装。
MCPファイルサーバーは、AIモデルが標準化されたAPIを介してローカルファイルシステム上でファイル操作を実行できるようにします。モデルコンテキストプロトコルSDKを使用して構築されており、ファイルの読み取り、作成、一覧表示のためのツールを提供します。
Related MCP server: filesystem-mcp-server
ファイルの作成: 指定した内容で新しいファイルを作成します
ファイルの読み取り: 既存のファイルの内容を読み取る
ディレクトリの内容の一覧表示: 詳細情報を含むファイルとディレクトリの一覧表示
パフォーマンス監視: エラー追跡とパフォーマンス監視のための組み込み Sentry 統合
npm installMCP ファイル サーバーを起動します。
node src/index.jsサーバーは、MCP プロトコルを使用して stdin/stdout を介して通信します。
指定されたパスに指定されたコンテンツを含む新しいファイルを作成します。
パラメータ:
filePath : ファイルを作成するパス
content : ファイルに書き込むコンテンツ
戻り値:
ファイルパスとサイズ情報を含む成功メッセージ
指定されたパスにあるファイルの内容を読み取ります。
パラメータ:
filePath : 読み取るファイルへのパス
戻り値:
ファイルの内容
指定されたパスにあるファイルとディレクトリを一覧表示します。
パラメータ:
path : 内容をリストするディレクトリパス
戻り値:
ファイル名、サイズ、タイプを含むマークダウンテーブル
SENTRY_DSN : エラー追跡用の Sentry データ ソース名 (オプション)
@modelcontextprotocol/sdk : MCP SDK パッケージ
zod : スキーマ検証
@sentry/node : エラー追跡とパフォーマンス監視
MCP プロトコルを通じてこれらのツールを呼び出す方法の例:
{
"name": "createfile",
"params": {
"filePath": "example/test.txt",
"content": "Hello, world!"
}
}{
"name": "readfile",
"params": {
"filePath": "example/test.txt"
}
}{
"name": "listfiles",
"params": {
"path": "example"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | Content to write to the file | |
| filePath | Yes | Path where the file should be created |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Path to the file to read |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0createfilelistfilesreadfileScored across 3 tools
The three tools have clearly distinct purposes: createfile for creating files, listfiles for listing files, and readfile for reading files. There is no overlap or ambiguity between these operations, making it easy for an agent to select the right tool for each task.
All tool names follow a consistent verb_noun pattern (createfile, listfiles, readfile) with no deviations. The naming is uniform and predictable, using lowercase letters and clear action-object combinations throughout.
With only three tools, the server feels thin for a file management domain, as it lacks essential operations like update, delete, or write to files. While the count is minimal, it covers basic CRUD aspects but leaves notable gaps in functionality.
The tool set is significantly incomplete for file management, missing critical operations such as updatefile, deletefile, and writefile. This creates dead ends for agents trying to perform common file workflows, leading to potential failures in tasks requiring modification or deletion.
Securely search and manage workspace context files for AI agents and teams.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
Browse and manage files in your Moxt AI workspace from any MCP client.
