How Wix scaled AI-native work to 5,000 employees with Willow
Read More
Enterprise Connectors
Willow Admin logo. Willow Admin MCP server connector.

Willow Admin MCP Server

Manage your Willow organization: users, groups, MCP servers, commands, skills, toolkits, and policies.

ToolsTools
30
Last updatedLast Updated
CategoryCategory
All
✓Enterprise-grade security
✓SSO & authentication ready
✓Full governance & audit logs

What is the Willow Admin MCP Server?

The Willow Admin MCP server gives AI agents structured, permission-aware access to Willow Admin through the Model Context Protocol. With 30 pre-built actions, agents can read, create, and update Willow Admin data on behalf of authorized users.

Willow ships the Willow Admin MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Willow Admin is being used by every AI agent in your stack.

Tools

List Users

List all users in the Webrix organization with pagination and search. Returns user details including name, email, machine user status, group associations, and timestamps.

Create User

Create a new user in the Webrix organization. The user will be created with the specified name and email address. The email must be unique and valid.

Update User

Update an existing user by email address. Only the fields provided will be updated; all other fields remain unchanged.

Delete User

Permanently delete a user by email address. This operation cannot be undone. All data associated with the user will be removed.

List Groups

List all groups in the Webrix organization with pagination and search. Returns group details including settings, user IDs, integration IDs, toolkit IDs, and skill IDs.

Create Group

Create a new group in the Webrix organization. Groups organize users and manage access to integrations, toolkits, and skills.

Update Group

Update an existing group by name. Only the fields provided will be updated; all other fields remain unchanged.

Delete Group

Permanently delete a group by name. All configuration and associations will be removed. This operation cannot be undone.

Add Integrations to Group

Add one or more integrations (MCP servers) to a group by their slugs. Integrations already present in the group are silently ignored.

List MCP Servers

List all MCP servers (connectors/integrations) in the Webrix organization. Returns server details including name, slug, status, configuration, and metadata.

Create MCP Server

Create a new MCP server integration. The slug is auto-generated from the name if not provided. Duplicate slugs get numeric suffixes.

Update MCP Server

Update an existing MCP server by slug. Only the fields provided will be updated; all other fields remain unchanged.

Delete MCP Server

Permanently delete an MCP server by slug. All configuration and data associated with the server will be removed. This operation cannot be undone.

List Commands

List all commands in the Webrix organization. Returns command details including name, slug, output content, arguments, and status.

Create Command

Create a new command with the specified name, slug, and output content. Commands can include arguments for dynamic content.

Update Command

Update an existing command by slug. Only the fields provided will be updated; all other fields remain unchanged.

Delete Command

Permanently delete a command by slug. This operation cannot be undone.

List Skills

List all skills in the Webrix organization. Returns skill details including name, slug, content, status, metadata, scripts, references, and assets.

Create Skill

Create a new skill. Skills are reusable AI agent configurations with markdown content, scripts, references, and assets. Created in draft status by default.

Update Skill

Update an existing skill by slug. Only the fields provided will be updated; all other fields remain unchanged.

Delete Skill

Permanently delete a skill by slug. The skill will be removed from all groups it was assigned to. This operation cannot be undone.

List Toolkits

List all toolkits in the Webrix organization. Returns toolkit details including status, configuration, integration tools, prompts, resources, and timestamps.

Create Toolkit

Create a new toolkit with the specified configuration. Toolkits group integration tools, prompts, and resources together.

Update Toolkit

Update an existing toolkit by slug. Only the fields provided will be updated; all other fields remain unchanged.

Delete Toolkit

Permanently delete a toolkit by slug. This operation cannot be undone.

Promote Toolkit

Promote a user-level toolkit to organization level. Optionally update the name, description, or slug during promotion.

List Policies

List all policies in the Webrix organization. Returns policy details including LLM prompts, result types, result options, and status.

Create Policy

Create a new policy with the specified name, LLM prompt, and result type. When result_type is 'options', the result_options array is required.

Update Policy

Update an existing policy by ID. Only the fields provided will be updated; all other fields remain unchanged.

Delete Policy

Permanently delete a policy by ID. This operation cannot be undone.

Customize tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

ReviewEdit descriptions
ConfigureChange arguments
ApproveSelect tools
Create NewAdd tool

Set Up Your Willow Admin MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json
{
  "mcpServers": {
    "willow-webrix-admin": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/webrix-admin"
    }
  }
}

Cursor

.cursor/mcp.json
{
  "mcpServers": {
    "willow-webrix-admin": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/webrix-admin"
    }
  }
}

Claude Code

CLI
claude mcp add willow-webrix-admin --transport http https://<org>.mcp-s.com/mcp/mcp/webrix-admin

n8n

HTTP Request Node
{
  "url": "https://<org>.mcp-s.com/mcp/mcp/webrix-admin",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for Willow Admin

Willow adds the layer Willow Admin and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

Willow Admin MCP Server FAQ

What is the Willow Admin MCP server?

The Willow Admin MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Willow Admin data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's Willow Admin MCP server different from the official one?

The official Willow Admin MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the Willow Admin MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the Willow Admin MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Willow Admin, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which Willow Admin actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow Willow Admin MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Willow Admin MCP locally, you'll see it.

What does the Willow Admin MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the Willow Admin MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.

Compare Willow MCP Gateway

See how Willow stacks up against other MCP platforms on governance, security, and enterprise readiness.

Your agents are already in the wild.

Give them a Basecamp. Go from AI chaos to AI work, in minutes.