Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery
Live 38 Actions

Egnyte MCP Server
for AI Agents

Connect your AI agent to StackOne's Egnyte MCP server and give it 38 MCP tools out of the box. Auth, tool execution, and security all managed.

Egnyte logo
Egnyte MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

38 Agent Actions

Create, read, update, and delete across Egnyte — and extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Egnyte MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Egnyte 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 Egnyte call.

Tools Discovery →

What is the Egnyte MCP Server?

A Egnyte MCP server lets AI agents read and write Egnyte data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Egnyte MCP server ships with 38 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 Egnyte MCP Tools

Every action from Egnyte's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Comments

  • Add Comment

    Add a comment (note) to a file or folder in Egnyte, identified by its absolute path.

  • List Comments

    List comments associated with a file or folder. Filter by path, ISO 8601 time window, and paginate with offset/count.

  • Get Comment

    Retrieve the details of a single comment by its UUID.

  • Delete Comment

    Delete a comment identified by its UUID.

File Content By Paths

  • Upload File Content By Path

    Upload a file's binary content to the given Egnyte path. Creates the file if it does not exist; overwrites it if it does.

  • Download File Content By Path

    Download the binary content of a file at the given Egnyte path. Optionally scope the download to a specific file version.

Groups

  • Create Group

    Create a new group on the Egnyte domain with the given displayName and initial member list.

  • List Groups

    List groups on the Egnyte domain. Supports SCIM-style filter syntax on displayName and paginates via startIndex/count.

  • Get Group

    Retrieve the details of a group by its groupId, including its displayName and member list.

  • Delete Group

    Delete a group by its groupId.

Link (v1)s

  • Create Link (v1)

    Create a shareable file, folder, or upload link for a given path. Configure accessibility (anyone / password / domain / recipients), optional password, expiry, click limit, notification, and recipient list.

  • Get Link (v1)

    Retrieve the details of a shareable link by its linkId.

  • Delete Link (v1)

    Delete a shareable link by its linkId.

Users

  • Create User

    Create a new user on the Egnyte domain. Requires userName, email, name (givenName + familyName), active flag, authType, and userType.

  • List Users

    List users on the Egnyte domain. Supports SCIM-style filter expressions, 1-based startIndex pagination, and count up to 100.

  • Get User

    Retrieve a single Egnyte user by their numeric user ID.

  • Update User

    Partially update an Egnyte user. Any subset of email, name (givenName/familyName), active, authType, userType, and other profile fields can be changed. At least one updatable field must be provided; empty PATCH bodies are rejected with USER_ERROR.

  • Delete User

    Delete an Egnyte user by their numeric user ID.

Other (20)

  • Get Events Cursor

    Fetch the current event stream cursor for this Egnyte tenant. Returns the latest and oldest event IDs along with a timestamp. Call this once to establish a starting cursor before polling `get_events_v2`.

  • List Events (v2)

    Poll the Egnyte event stream for file system, note, and permission changes starting after a given cursor ID. Wait at least 5 minutes between polls to avoid rate-limiting.

  • Get File Or Folder Metadata (v2)

    Retrieve metadata for a file or folder at the given Egnyte path. Optionally list folder contents, include permissions, locks, collaboration info, and custom metadata.

  • Get File Or Folder Metadata By ID

    Retrieve metadata for a file or folder using its persistent ID (group_id for files, folder_id for folders).

  • Get Folder Statistics By ID

    Retrieve aggregate statistics (item counts, sizes) for a folder identified by its folder_id.

  • Download File Content By ID

    Download the binary content of a file identified by its persistent group_id. Optionally scope the download to a specific file version.

  • List Links (v2)

    List shareable file and folder links on the domain. Filter by path, username, link type, or accessibility. Paginate with offset/count.

  • Get Effective Permissions For User

    Retrieve the effective folder permissions for a specific user on a specific folder path. Both `username` and `folder` are required.

  • Search Files And Folders (v2)

    Search for files and folders across the Egnyte domain using keywords and/or custom metadata filters. Supports pagination, time window filtering, sort, and field/similarity filters.

  • Get User Info

    Return basic information (username, email, first_name, last_name, phone, is_admin, is_service_account) about the user associated with the current OAuth access token. Used as the connection health-check.

  • List Trash Contents (v2)

    List items in the Egnyte trash with extended sort options and a deletedBy/date-range filter. Only administrators or power users with trash management privileges can access this endpoint.

  • Delete File Or Folder (v2)

    Delete a file or folder at the given path. Optionally scope deletion to a single file version via `entry_id`.

  • Delete File Or Folder By ID

    Delete a file or folder identified by its persistent ID (group_id / folder_id). Optionally scope deletion to a single file version.

  • File Or Folder Operation (v2)

    Perform a filesystem operation on a file or folder at the given path — create a folder, move, copy, rename, lock, or unlock.

  • File Or Folder Operation By ID

    Move or copy a file or folder identified by its persistent ID (group_id / folder_id).

  • Chunked Upload By File ID

    Upload a single chunk of a large file (identified by its persistent group_id) as part of a chunked upload. Recommended chunk size is 100 MB; min 10 MB, max 1 GB. All chunks except the last must be the same size.

  • Modify Folder Options

    Update folder-level configuration such as description, link behaviour, move/delete restrictions, permission inheritance, and email notifications for a folder at the specified path.

  • Replace Group

    Fully replace a group — set its displayName and the complete member roster in one call. Any existing member NOT in the supplied list is dropped.

  • Partially Update Group

    Partially update a group — rename via `displayName` or remove members incrementally via a `members` array of `{value, operation:'delete'}` objects. Egnyte does NOT accept SCIM 2.0 PatchOp `schemas`/`Operations` arrays here; fields are sent directly.

  • Restore Or Purge Trash Items

    Restore items from the Egnyte trash back to their original location, or permanently delete (purge) them. Provide the action and up to 10 trash item IDs.

Set Up Your Egnyte MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Egnyte in under 10 lines of code.

Agent Frameworks

Claude Desktop
{
  "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

Egnyte MCP Server FAQ

Does StackOne have a Egnyte MCP server?
Yes. StackOne offers a hosted Egnyte MCP server with 38 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Egnyte MCP server vs direct API integration — what's the difference?
A Egnyte MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Egnyte. A Egnyte MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Egnyte at runtime. StackOne provides both.
How does Egnyte authentication work for AI agents?
Egnyte authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Egnyte account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Egnyte MCP tools vulnerable to prompt injection?
Yes — Egnyte MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Egnyte agent and how do I avoid it?
Context bloat happens when Egnyte tool schemas and API responses eat your Egnyte agent's memory, preventing it from reasoning effectively. A single Egnyte query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Egnyte agent can access?
Yes — you can limit which actions your Egnyte agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Egnyte MCP server?
Yes — you can create custom agent actions for your Egnyte MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Egnyte's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Egnyte MCP server?
Skip a Egnyte MCP server if your integration is purely software-to-software — direct Egnyte API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Egnyte actions at runtime.
What AI frameworks and AI clients does the StackOne Egnyte MCP server support?
The StackOne Egnyte MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

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.