SharePoint MCP Server
for AI Agents
Connect your AI agent to StackOne's SharePoint MCP server and give it ready-to-use MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
19 Agent Actions
Create, read, update, and delete across SharePoint — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your SharePoint MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every SharePoint tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every SharePoint call.
Tools Discovery →What is the SharePoint MCP Server?
A SharePoint MCP server lets AI agents read and write SharePoint data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's SharePoint MCP server ships with pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All SharePoint MCP Tools
Every action from SharePoint's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Sites
- List Sites
Search and retrieve SharePoint sites across the organization using keyword search. This is the primary entry point for discovering sites - use "*" to list all accessible sites or provide specific search terms to find sites by name, description, or content.
- Get Site
Retrieve complete metadata for a specific SharePoint site by its unique identifier, including configuration details, timestamps, and optionally related resources like document libraries and lists. Use this after list_sites to get full site details or to verify site existence before performing operations.
- Search Sites
Find SharePoint sites matching a keyword search query with relevance-ranked results. Use this when you have a search term or site name fragment from a user and need to find matching sites. Unlike list_sites, search is required here and results are ordered by relevance rather than alphabetically.
Items
- List Items
Retrieve all items from a SharePoint list as structured data records with their field values. Supports filtering by column values and selecting specific columns. IMPORTANT - You must use expand=fields to get column data as field values are not included by default.
- Get Item
Retrieve a single item from a SharePoint list by its ID with complete metadata and field values. Use this to get detailed item data before updates, verify item existence, retrieve the web URL for sharing, or get the eTag for optimistic concurrency control.
Other (14)
- Get Site By Path
Retrieve a SharePoint site using its URL hostname and server-relative path instead of an opaque ID. This is the preferred method when you have a SharePoint URL from a user, document link, or browser address bar and need to resolve it to a site resource with its API-usable ID.
- List Subsites
Retrieve all immediate child subsites nested under a parent SharePoint site. Use this to navigate site hierarchies, discover departmental or project sites organized under a parent team site, and build site tree structures for navigation interfaces.
- Get Root Site
Retrieve the tenant's root SharePoint site collection without needing to know its ID. This is the primary entry point for discovering the organization's SharePoint structure, hostname, and top-level sites when starting fresh without prior context.
- Get Site Columns
Retrieve all site column definitions available at the site level for schema discovery. Site columns are reusable metadata field templates that can be added to multiple lists within the site, promoting consistent data schemas across the organization.
- Get Site Content Types
Retrieve all content type definitions available at a SharePoint site for understanding document and item templates. Content types bundle metadata columns with settings and behaviors, enabling consistent categorization of documents like contracts, invoices, or project documents across lists and libraries.
- List Site Lists
Retrieve all SharePoint lists in a site including document libraries, custom data lists, task lists, and system lists. Use this to discover available structured data containers before querying their items or to inventory a site's data assets.
- Get List
Retrieve detailed metadata for a specific SharePoint list including its template type, content type settings, creation date, and web URL. Use this to verify list existence, get sharing URLs, or understand list configuration before performing data operations.
- Get List Columns
Retrieve the complete schema of all columns in a SharePoint list including their data types, validation rules, and configuration. Essential for understanding list structure before querying items, building forms, or mapping data fields.
- Get List Operations
Retrieve the status of long-running background operations on a SharePoint list such as bulk imports, content type synchronization, or schema changes. Use this to monitor async operation progress, identify failed operations, or audit operation history.
- List Site Drives
Retrieve all document libraries (drives) available in a SharePoint site including their storage quota, ownership, and configuration. Use this to discover available file storage locations before browsing files or uploading documents.
- Get Drive
Retrieve detailed metadata for a specific SharePoint document library including current storage quota status, ownership information, and configuration. Use this to check storage availability before uploads, monitor quota usage, or get the shareable web URL.
- List Drive Root Children
List all files and folders at the root level of a SharePoint document library. Returns item metadata including name, size, type (file/folder), MIME type, and timestamps. Use list_drive_item_children to browse into subfolders.
- List Drive Item Children
List all files and folders within a specific folder in a SharePoint document library. Use this to navigate into subfolders after using list_drive_root_children to browse the root level.
- Get Drive Item
Retrieve complete metadata for a specific file or folder in SharePoint, including size, MIME type, permissions, and sharing links.
Set Up Your SharePoint MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to SharePoint in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Check More Documents & Knowledge MCP Servers
134+ actions
101+ actions
96+ actions
95+ actions
92+ actions
80+ actions
80+ actions
Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
SharePoint MCP Server FAQ
Does StackOne have a SharePoint MCP server?
SharePoint MCP server vs direct API integration — what's the difference?
How does SharePoint authentication work for AI agents?
origin_owner_id.Are SharePoint MCP tools vulnerable to prompt injection?
What is the context bloat of a SharePoint agent and how do I avoid it?
Can I limit which actions my SharePoint agent can access?
Can I create custom agent actions for my SharePoint MCP server?
When should I NOT use a SharePoint MCP server?
What AI frameworks and AI clients does the StackOne SharePoint MCP server support?
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.