What authentication method does the SharePoint Connector Library use?
It uses app-only authentication with a Client ID and Client Secret obtained from an Azure AD application registration.
@mhmd2015
基本信息
Create MCP server for accessing SharePoint Online
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
SharePoint MCP is a modular .NET server that exposes Microsoft Graph API and Semantic Kernel capabilities to provide AI-driven access to SharePoint Online data. It acts as a central hub for search functionality, using app-only authentication and a separate client interface such as Gemini AI for user interaction.
Set up the three-module architecture: deploy the .NET MCP Server (configured with Semantic Kernel), register an Azure AD application with Graph API permissions (e.g., Sites.Read.All) and store the client secret securely, then build an MCP Client (e.g., using Gemini AI SDK) that calls the server’s /api/sharepoint/search endpoint with user queries. No specific commands or config keys are detailed beyond this workflow.
It uses app-only authentication with a Client ID and Client Secret obtained from an Azure AD application registration.
The application requires permission such as Sites.Read.All (or more granular) and must have admin consent granted in Azure AD.
The server exposes an endpoint such as `/api/sharepoint/search` that accepts search queries and returns SharePoint results.
The stack includes .NET, Microsoft Graph SDK, Semantic Kernel, and the Gemini AI SDK for the client interface.
No – it is a backend server only. The user interface is provided by a separate MCP Client (e.g., a Gemini‑powered chat application).

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
评论