Filesystem MCP Server
sistema de archivos
Un servidor de Protocolo de Contexto de Modelo (MCP) creado con mcp-framework.
Inicio rápido
# Install dependencies
npm install
# Build the project
npm run build
Related MCP server: MCP Tools
Estructura del proyecto
filesystem/
├── src/
│ ├── tools/ # MCP Tools
│ │ └── ExampleTool.ts
│ └── index.ts # Server entry point
├── package.json
└── tsconfig.jsonAgregar componentes
El proyecto incluye una herramienta de ejemplo en src/tools/ExampleTool.ts . Puedes agregar más herramientas mediante la CLI:
# Add a new tool
mcp add tool my-tool
# Example tools you might create:
mcp add tool data-processor
mcp add tool api-client
mcp add tool file-handlerDesarrollo de herramientas
Ejemplo de estructura de herramienta:
import { MCPTool } from "mcp-framework";
import { z } from "zod";
interface MyToolInput {
message: string;
}
class MyTool extends MCPTool<MyToolInput> {
name = "my_tool";
description = "Describes what your tool does";
schema = {
message: {
type: z.string(),
description: "Description of this input parameter",
},
};
async execute(input: MyToolInput) {
// Your tool logic here
return `Processed: ${input.message}`;
}
}
export default MyTool;Publicación en npm
Actualice su paquete.json:
Asegúrese de que
namesea único y siga las convenciones de nomenclatura de npmEstablecer
versionapropiadaAñadir
description,author,license, etc.Verificar los puntos
binen el archivo de entrada correcto
Construir y probar localmente:
npm run build npm link filesystem # Test your CLI locallyInicie sesión en npm (cree una cuenta si es necesario):
npm loginPublica tu paquete:
npm publish
Después de publicar, los usuarios pueden agregarlo a su cliente de escritorio Claude (leer a continuación) o ejecutarlo con npx
## Using with Claude Desktop
### Local Development
Add this configuration to your Claude Desktop config file:
**MacOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
**Windows**: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"filesystem": {
"command": "node",
"args":["/absolute/path/to/filesystem/dist/index.js"]
}
}
}Después de la publicación
Agregue esta configuración a su archivo de configuración de Claude Desktop:
MacOS : ~/Library/Application Support/Claude/claude_desktop_config.json Windows : %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["filesystem"]
}
}
}Construcción y pruebas
Realizar cambios en sus herramientas
Ejecute
npm run buildpara compilarEl servidor cargará automáticamente sus herramientas al iniciarse
Más información
This server cannot be deployed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA Model Context Protocol server that enables AI assistants like Claude to perform Python development tasks through file operations, code analysis, project management, and safe code execution.9MIT
- AlicenseNot gradedqualityDmaintenanceA custom Model Context Protocol server that gives Claude Desktop and other LLMs access to file system operations and command execution capabilities through standardized tool interfaces.23Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that allows AI models to safely access and interact with local file systems, enabling reading file contents, listing directories, and retrieving file metadata.2 npm10MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables Claude Desktop to perform file operations like reading, writing, listing directories, and managing files through natural language commands.MIT