Un servidor de protocolo de contexto de modelo que proporciona acceso a SharePoint organizacional.
Componente | Operación | Recurso | Recurso dinámico | Herramienta |
Usuarios | ❌ | ❌ | ❌ | |
Leer usuario | ❌ | ❌ | ❌ | |
Buscar usuario | ❌ | ❌ | ❌ | |
Sitios | ❌ | ❌ | ❌ | |
Lista de sitios | ✅ | ❌ | ❌ | |
Obtener detalles del sitio | ❌ | ❌ | ❌ | |
Crear subsitio | ❌ | ❌ | ❌ | |
Eliminar sitio | ❌ | ❌ | ❌ | |
Unidades | ❌ | ❌ | ❌ | |
Lista de carpetas | ❌ | ❌ | ❌ | |
Carpetas de búsqueda | ❌ | ❌ | ✅ | |
Crear carpeta | ❌ | ❌ | ❌ | |
Eliminar carpeta | ❌ | ❌ | ❌ | |
Subir archivo | ❌ | ❌ | ❌ | |
Elementos de la lista | ❌ | ✅ | ❌ | |
Descargar archivo | ❌ | ❌ | ✅ | |
Leer archivo | ✅ | ❌ | ❌ | |
Mover archivo | ❌ | ❌ | ❌ | |
Copiar archivo | ❌ | ❌ | ❌ | |
Liza | ❌ | ❌ | ❌ | |
Crear lista | ❌ | ❌ | ❌ | |
Lista de lectura | ❌ | ❌ | ❌ | |
Añadir a la lista | ❌ | ❌ | ❌ | |
Lista de actualizaciones | ❌ | ❌ | ❌ | |
Eliminar lista | ❌ | ❌ | ❌ | |
Calendario | ❌ | ❌ | ❌ | |
Crear evento | ❌ | ❌ | ❌ | |
Leer evento | ❌ | ❌ | ❌ | |
Evento de actualización | ❌ | ❌ | ❌ | |
Eliminar evento | ❌ | ❌ | ❌ |
resumen del documento
encontrar documentos relevantes
carpeta de exploración
Related MCP server: SharePoint MCP Server
Copiar .env.example como .env
Llene los campos requeridos
Desde la raíz
npx @modelcontextprotocol/inspector -e TENANT_ID=your_tenant_id -e CLIENT_ID=your_client_id -e CLIENT_SECRET=your_client_secret -e SITE_ID=your_site_id -e DRIVE_ID=your_drive_id -- node dist/index.jsPara usar este servidor con la aplicación Claude Desktop, agregue la siguiente configuración a la sección "mcpServers" de su claude_desktop_config.json :
Compilación y etiqueta de Docker docker build -t mcp/sharepoint .
{
"mcpServers": {
"sharepoint": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"-e", "DOCKER_CONTAINER=true",
"-e", "TENANT_ID=your-tenant-id",
"-e", "CLIENT_ID=your-client-id",
"-e", "CLIENT_SECRET=your-client-secret",
"-e", "SITE_ID=your-site-id",
"-e", "DRIVE_ID=your-drive-id",
"mcp/sharepoint"
]
}
}
}pnpm run build{
"mcpServers": {
"sharepoint": {
"command": "node",
"args": ["run", "start"],
"env": {
"TENANT_ID": "your-tenant-id",
"CLIENT_ID": "your-client-id",
"CLIENT_SECRET": "your-client-secret",
"SITE_ID": "your-site-id",
"DRIVE_ID": "your-drive-id",
}
}
}
}Este servidor MCP cuenta con la licencia MIT. Esto significa que puede usar, modificar y distribuir el software libremente, sujeto a los términos y condiciones de la licencia MIT. Para más detalles, consulte el archivo de licencia en el repositorio del proyecto.
| Name | Required | Description | Default |
|---|---|---|---|
| maxResults | No | Maximum number of results to return (as a string) | |
| query | Yes | Search query to find documents |
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.
v1.0.0search-documentsScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'search-documents' has a distinct purpose that cannot be confused with any other tool in the set.
The naming is trivially consistent as there is only one tool. The tool name 'search-documents' follows a verb-noun pattern, which is clear and predictable, though this cannot be evaluated across multiple tools.
A single tool is too few for a server named 'Sharepoint MCP Server', which suggests a broader domain like document management, collaboration, or file handling. This minimal set likely leaves significant gaps in functionality, making it inappropriate for the apparent scope.
The tool set is severely incomplete for a Sharepoint domain. With only a search tool, there are obvious gaps in CRUD operations (e.g., create, update, delete documents), user management, or other typical Sharepoint functionalities, which will cause agent failures in handling common workflows.
Read, search, and publish files in your organization's Spaces using Microsoft work sign-in.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Permissioned access to Outlook, OneDrive and Teams via the user's own Microsoft account
Securely search and manage workspace context files for AI agents and teams.